© 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. 33-TRANSCODER-HP
    7. 52655
    Prev
    Next
    INDEX
    Explanations

    export

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¾ĵåĩº
    -0.31
     è¾ĵåĩº
    -0.29
     output
    -0.26
    éĺ²ç©º
    -0.25
    æĪijæĺ¯
    -0.25
    ä¸Ńæĸ°
    -0.25
    çŁŃæľŁ
    -0.25
    poser
    -0.25
     Output
    -0.24
    æĪĺäºī
    -0.24
    POSITIVE LOGITS
    Invariant
    0.28
    eward
    0.28
    elihood
    0.27
    abled
    0.26
    iability
    0.26
    åĬ²
    0.26
    ence
    0.26
    ULE
    0.26
    ICLE
    0.25
    eyJ
    0.25
    Activations Density 0.007%

    No Known Activations