© 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. 24-TRANSCODER-HP
    7. 149565
    Prev
    Next
    INDEX
    Explanations

    article snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lookup
    -0.06
     Coordinates
    -0.06
     Relation
    -0.06
     Belgi
    -0.06
     Credits
    -0.06
     Rape
    -0.06
     Parameter
    -0.06
     Prefix
    -0.06
     Relations
    -0.06
     Couples
    -0.06
    POSITIVE LOGITS
     pan
    0.07
    —if
    0.07
     imper
    0.07
     interconnected
    0.06
    —the
    0.06
    —and
    0.06
     wh
    0.06
     “
    0.06
    —all
    0.06
    -to
    0.06
    Activations Density 0.986%

    No Known Activations