© 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. 40093
    Prev
    Next
    INDEX
    Explanations

    far

    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
     K
    -0.28
    _CHOICES
    -0.26
    CATEGORY
    -0.25
     GDK
    -0.25
     G
    -0.25
    .CreateCommand
    -0.24
     Åļ
    -0.24
     Åģ
    -0.24
     Science
    -0.24
    èmes
    -0.24
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.54
     further
    0.54
    éĢ²ä¸ĢæŃ¥
    0.46
    Further
    0.44
    -remove
    0.42
    remove
    0.41
     Further
    0.39
     removing
    0.39
     furthermore
    0.38
    removed
    0.38
    Activations Density 0.231%

    No Known Activations