© 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. 40154
    Prev
    Next
    INDEX
    Explanations

    Licensed

    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
    èĢĮæĺ¯
    -0.30
     ‘
    -0.28
     Into
    -0.28
    _into
    -0.28
    å¼ĢäºĨ
    -0.28
    ’S
    -0.27
    Into
    -0.26
    è¿ĽäºĨ
    -0.26
    ’re
    -0.26
    èµ°åħ¥
    -0.26
    POSITIVE LOGITS
    ä¸į
    0.27
    ä»ĸ
    0.27
    åıĶ
    0.26
    stantiate
    0.26
    ä¸ľè¥¿
    0.26
    quel
    0.26
    .splice
    0.26
     he
    0.26
    หลวà¸ĩ
    0.25
    sth
    0.25
    Activations Density 2.191%

    No Known Activations