© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88781
    Prev
    Next
    INDEX
    Explanations

    Informal, conversational text

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    å½ĵåľ°äºº
    -0.28
    çį¾
    -0.26
    éªĨ
    -0.24
    oped
    -0.24
    æľ«ç«¯
    -0.24
     oluÅŁtur
    -0.24
    any
    -0.24
    åįłåľ°
    -0.24
    æł¸å¿ĥæĬĢæľ¯
    -0.24
    icional
    -0.23
    POSITIVE LOGITS
    éĥ½ä¸įèĥ½
    0.27
     sight
    0.27
    iliar
    0.26
    vez
    0.25
    arella
    0.24
    ä¼¼ä¹İæĺ¯
    0.24
    å¤Ħ
    0.24
    éĥ½æ²¡æľī
    0.24
     div
    0.23
    utenberg
    0.23
    Activations Density 0.005%

    No Known Activations