© 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. 18-TRANSCODER-HP
    7. 88489
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ī
    -0.30
    oref
    -0.28
    LOY
    -0.27
    çĸ£
    -0.25
     Vas
    -0.24
     Walters
    -0.24
    æݧèĤ¡
    -0.24
    objective
    -0.24
    第ä¸ĢæĿ¡
    -0.24
    æ±īåŃIJ
    -0.24
    POSITIVE LOGITS
    tracts
    0.29
    顺
    0.26
    æī©å¼ł
    0.25
    обÑīе
    0.25
    leine
    0.24
    osa
    0.24
    å¹´ä¹ĭä¹ħ
    0.24
    åħ¬åħĥåīį
    0.24
    çĺ¸
    0.24
    typescript
    0.24
    Activations Density 37.126%

    No Known Activations

    This feature has no known activations.