© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39782
    Prev
    Next
    INDEX
    Explanations

    ed

    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
     routinely
    -0.26
    è¿Ľä¸ĢæŃ¥
    -0.25
     formulations
    -0.25
     consistently
    -0.25
    æĽ´å¤§çļĦ
    -0.24
     drastically
    -0.24
    äºĮæĪĺ
    -0.24
     accomplishments
    -0.24
     sizing
    -0.24
     вÑĭвод
    -0.24
    POSITIVE LOGITS
    g
    0.40
    rene
    0.35
    anos
    0.34
    ano
    0.33
    ania
    0.33
    iah
    0.32
    gio
    0.32
    lace
    0.32
    leys
    0.31
    aly
    0.31
    Activations Density 1.177%

    No Known Activations