© 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. 27-TRANSCODER-HP
    7. 9618
    Prev
    Next
    INDEX
    Explanations

    back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earn
    -0.28
    ä»ĵ
    -0.26
    é«ĺ度éĩįè§Ĩ
    -0.25
     abst
    -0.25
     snug
    -0.25
     nag
    -0.25
    çĻ½é©¬
    -0.24
    care
    -0.23
     awake
    -0.23
     sense
    -0.23
    POSITIVE LOGITS
    è°ĥéħį
    0.26
    @a
    0.26
    èµ°äºĨ
    0.25
    åľī
    0.25
     Vander
    0.24
     Strauss
    0.24
    转移åĪ°
    0.24
    調
    0.23
    ä¸ĭæĿ¥
    0.23
    ì¡°ìĤ¬
    0.23
    Activations Density 0.004%

    No Known Activations