© 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. 112769
    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
    erte
    -0.32
    creen
    -0.28
    enes
    -0.26
    usta
    -0.26
    åıij
    -0.26
    acles
    -0.26
    erset
    -0.26
    说æĺ¯
    -0.25
    enza
    -0.25
    ets
    -0.25
    POSITIVE LOGITS
    (operator
    0.24
     industri
    0.23
    Caps
    0.23
     вне
    0.23
    _caps
    0.23
     наÑĢÑĥÑĪен
    0.23
     corporate
    0.23
     Indust
    0.22
     rehabilit
    0.22
     hemorrh
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.