© 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. 112745
    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
    çĥŁçģ«
    -0.29
    ably
    -0.26
     (--
    -0.26
    kest
    -0.25
     motorcycle
    -0.25
    驾
    -0.24
    ths
    -0.23
    **)
    -0.23
    第ä¸Ģ天
    -0.23
     pressure
    -0.23
    POSITIVE LOGITS
     ENUM
    0.31
    cheid
    0.30
    soever
    0.27
    ermen
    0.27
    ÃŃm
    0.26
    ingles
    0.26
    纬
    0.25
    feito
    0.24
    anges
    0.23
     Enum
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.