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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 195
    Prev
    Next
    INDEX
    Explanations

    Discovering something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éķ¿è¿ľ
    -0.30
    imo
    -0.27
    IMO
    -0.27
    ä¸įæľį
    -0.25
    å°±ä¸į
    -0.25
     cath
    -0.25
    çļĦä¸Ģéĥ¨åĪĨ
    -0.25
    ½Ķ
    -0.24
    olv
    -0.24
    Towards
    -0.24
    POSITIVE LOGITS
    å½ĵåĪĿ
    0.28
    ounters
    0.27
    rium
    0.26
     Covenant
    0.25
     Pickup
    0.25
     convergence
    0.24
    prix
    0.24
    æī§
    0.24
     Riders
    0.23
    <Service
    0.23
    Activations Density 0.052%

    No Known Activations