© 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. 87495
    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
     gestures
    -0.27
    é»ĺå¥ij
    -0.27
    odcast
    -0.27
    hythm
    -0.26
    ä¾Ŀæ³ķ
    -0.26
    ä¸ī家
    -0.26
     gest
    -0.25
    roc
    -0.25
     gesture
    -0.25
    udy
    -0.25
    POSITIVE LOGITS
    éĩĿ
    0.27
    PH
    0.25
    atts
    0.25
    æŃ£å½ĵ
    0.24
     PX
    0.24
    Ñģен
    0.24
    anus
    0.23
    tal
    0.23
    åįĬå²Ľ
    0.23
     PH
    0.23
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.