© 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. 25-TRANSCODER-HP
    7. 109235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dbg
    -0.29
    èĥ½å¤Łåľ¨
    -0.28
    transition
    -0.28
    íĮĶ
    -0.26
    å§ĭ
    -0.26
     transition
    -0.26
     Cond
    -0.25
    è§ĦèĮĥ
    -0.25
    å¾Ĵ
    -0.25
    æĹ¢èĥ½
    -0.25
    POSITIVE LOGITS
     hÆ°á»Łng
    0.25
     breathe
    0.24
    举
    0.24
    沧æ¡ij
    0.24
    çĥŁçģ«
    0.24
    bbox
    0.24
    aled
    0.24
     leverage
    0.24
    ıklı
    0.23
    è¯Ŀè¯Ń
    0.23
    Activations Density 0.148%

    No Known Activations

    This feature has no known activations.