© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141291
    Prev
    Next
    INDEX
    Explanations

    Personal stories and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relationship
    -0.34
     relationships
    -0.34
    relationships
    -0.33
    relationship
    -0.32
    çļĦåħ³ç³»
    -0.32
     Relationship
    -0.32
    åħ³ç³»
    -0.31
    Relationship
    -0.30
     relation
    -0.29
     relations
    -0.28
    POSITIVE LOGITS
    èĥĮéĥ¨
    0.26
    åĴ½åĸī
    0.26
    uida
    0.25
    iface
    0.25
    硬度
    0.24
     sore
    0.24
    æĪªæŃ¢
    0.24
    åīįåĪĹ
    0.24
     countered
    0.23
    åĪ°è´¦
    0.23
    Activations Density 22.154%

    No Known Activations