© 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. 112612
    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
    ç§ĭåŃ£
    -0.30
    å°Ħæīĭ
    -0.29
    çĭĤ
    -0.28
    /documents
    -0.26
    ugu
    -0.26
    ä¸ĸ家
    -0.26
    èĥ¡åŃIJ
    -0.25
    åĩłç§į
    -0.24
    çªģå¦Ĥåħ¶
    -0.24
    æľīæľºç»ĵåIJĪ
    -0.24
    POSITIVE LOGITS
    istro
    0.27
    ä½į
    0.27
     HRESULT
    0.25
     morale
    0.25
     Ston
    0.25
    eyes
    0.24
     moving
    0.24
    leitung
    0.24
     hom
    0.24
    мÑı
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.