© 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. 129446
    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
    sembler
    -0.27
    sembling
    -0.26
    å§Ĭ
    -0.25
    Atl
    -0.25
    éĺ¡
    -0.25
    ç»Ļä½łä»¬
    -0.24
    èĢģ年人
    -0.24
    -progress
    -0.24
    structions
    -0.24
    ornings
    -0.23
    POSITIVE LOGITS
    éĿ¢åīį
    0.27
    ivated
    0.25
     vice
    0.25
    è§ħ
    0.24
    åħ¨å¹´
    0.24
     bow
    0.24
    notes
    0.24
    åĪģ
    0.24
    irting
    0.24
     Lap
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.