© 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. 30-TRANSCODER-HP
    7. 96030
    Prev
    Next
    INDEX
    Explanations

    open spaces and concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .dynamic
    -0.29
    á»ĵng
    -0.26
    åĬ¨æĢģ
    -0.26
    rica
    -0.26
    влеÑĩен
    -0.26
    ibe
    -0.26
    æ¶ĪçģŃ
    -0.25
    ât
    -0.25
    thouse
    -0.25
     enslaved
    -0.24
    POSITIVE LOGITS
    oose
    0.25
    -pres
    0.25
    çĶ»
    0.25
     widest
    0.25
    æ§
    0.25
     bearing
    0.25
    .hex
    0.24
    KHTML
    0.24
    çĶ¨è½¦
    0.24
    PIO
    0.24
    Activations Density 0.010%

    No Known Activations