© 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. 149989
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    é¦
    -0.29
    çıĤ
    -0.26
     fires
    -0.25
    ç½ijç«Ļåľ°åĽ¾
    -0.25
    客
    -0.25
     caste
    -0.24
    åIJĥäºĨ
    -0.24
    ¥
    -0.24
     lives
    -0.24
     nesting
    -0.24
    POSITIVE LOGITS
    nam
    0.29
    errat
    0.29
    qe
    0.27
    [top
    0.25
    arat
    0.25
     Monsters
    0.24
    äºĮæīĭ
    0.24
    intendo
    0.24
    daq
    0.24
     вÑĭÑħод
    0.24
    Activations Density 0.774%

    No Known Activations

    This feature has no known activations.