© 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. 30-TRANSCODER-HP
    7. 97082
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    omba
    -0.26
    orre
    -0.25
    abh
    -0.25
    åĩŃåĢŁ
    -0.24
    帰ãĤĬ
    -0.24
    å¹ķ
    -0.24
    å¾ħãģ¡
    -0.24
     supposed
    -0.23
     called
    -0.23
    uur
    -0.23
    POSITIVE LOGITS
    ashes
    0.30
    _prefs
    0.29
    ,ep
    0.27
    èİĨ
    0.26
     TAR
    0.25
    _maker
    0.25
    äºĮæľŁ
    0.25
    æĦŁæŁĵ
    0.25
    è¯Ħæ¯Ķ
    0.25
    prite
    0.24
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.