© 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. 107094
    Prev
    Next
    INDEX
    Explanations

    research

    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
    æī¶
    -0.28
    tribute
    -0.27
    ilion
    -0.26
    огÑĢаÑĦ
    -0.26
    gebung
    -0.26
    optgroup
    -0.26
    enie
    -0.26
    ç®Ģæĺĵ
    -0.25
    ãĥŃãĥ³
    -0.25
     Gim
    -0.24
    POSITIVE LOGITS
    s
    0.43
    sheets
    0.28
     latter
    0.27
    ä¸Ģå°ģ
    0.27
    ä¸Ģç¬Ķ
    0.26
    sar
    0.25
    äºĨä¸Ģéģį
    0.25
    訪
    0.25
     financing
    0.24
    sad
    0.24
    Activations Density 16.212%

    No Known Activations