© 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. 88056
    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
    IENT
    -0.22
    mund
    -0.21
    RAFT
    -0.21
    YRO
    -0.21
    æķ¬è¯·
    -0.21
    icter
    -0.21
    WER
    -0.20
     nause
    -0.20
     gob
    -0.20
    éĿ
    -0.20
    POSITIVE LOGITS
    ats
    0.23
    .Convert
    0.22
     P
    0.22
    ada
    0.21
    .:
    0.21
    0.21
    ars
    0.21
    !
    0.21
    em
    0.21
     Christian
    0.21
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.