© 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. 35-TRANSCODER-HP
    7. 40448
    Prev
    Next
    INDEX
    Explanations

    W

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Registr
    -0.26
    HS
    -0.26
    OPSIS
    -0.25
    MHz
    -0.25
    SCR
    -0.25
    kbd
    -0.25
    MEM
    -0.24
    scala
    -0.24
     unaware
    -0.24
    FunctionFlags
    -0.24
    POSITIVE LOGITS
    rim
    0.31
    ring
    0.31
     omin
    0.29
    impl
    0.28
    çŀĦåĩĨ
    0.28
     implications
    0.27
     implication
    0.27
    触åĬ¨
    0.27
     indications
    0.27
     aim
    0.26
    Activations Density 0.196%

    No Known Activations