© 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. 107128
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    fähig
    -0.28
    ìĤ¬ë¥¼
    -0.27
    @endsection
    -0.26
    éĢĤåºĶ
    -0.26
    inati
    -0.26
     ?.
    -0.26
    Å¡e
    -0.26
    é¡»
    -0.25
    èĹIJ
    -0.24
     us
    -0.24
    POSITIVE LOGITS
     altogether
    0.27
    æīįæĺ¯çľŁæŃ£
    0.26
    çľĭä½ł
    0.26
    ters
    0.25
    pair
    0.25
    åŀ«
    0.24
    éĤ£åĦ¿
    0.24
    STS
    0.24
    rai
    0.24
    nom
    0.24
    Activations Density 0.933%

    No Known Activations