© 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. 22-TRANSCODER-HP
    7. 98341
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieties
    -0.21
     Nack
    -0.20
    _simps
    -0.20
    .modelo
    -0.19
    á»īnh
    -0.19
    æѤæŶ
    -0.19
     slippery
    -0.19
    åıį转
    -0.19
    _syntax
    -0.19
     fib
    -0.19
    POSITIVE LOGITS
     maur
    0.21
     Maxim
    0.21
    others
    0.20
    some
    0.19
    touches
    0.19
    Reason
    0.19
    çĿĢ
    0.19
     others
    0.19
    oust
    0.19
     ape
    0.19
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.