© 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. 20-TRANSCODER-HP
    7. 63468
    Prev
    Next
    INDEX
    Explanations

    reports and studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udes
    -0.31
    .Parser
    -0.30
    æĹ¶è¡¨ç¤º
    -0.27
    äºĭãģĮ
    -0.27
    ialog
    -0.26
    _=
    -0.26
    _',
    -0.25
    itech
    -0.25
    еÑĤÑĮ
    -0.25
    éĺ³
    -0.24
    POSITIVE LOGITS
    .INSTANCE
    0.28
    çĦĵ
    0.28
    áĥª
    0.27
    azzi
    0.25
    zs
    0.25
    èļĮ
    0.24
     finishes
    0.24
     entert
    0.23
    è¥Ħ
    0.23
     retal
    0.23
    Activations Density 10.789%

    No Known Activations