© 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. 107336
    Prev
    Next
    INDEX
    Explanations

    on

    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
    ivel
    -0.28
    รวà¸Ķ
    -0.24
    æĮ¹
    -0.24
    -ts
    -0.24
    iper
    -0.24
     detections
    -0.24
    reich
    -0.24
     IL
    -0.24
     Incident
    -0.24
    ssi
    -0.24
    POSITIVE LOGITS
    çĽ¸å¯¹äºİ
    0.29
    appendTo
    0.27
    after
    0.27
     after
    0.27
    åIJİçļĦ
    0.26
    edith
    0.26
    åIJĮ樣
    0.26
    ROM
    0.26
    åIJĮæł·
    0.25
     compared
    0.25
    Activations Density 55.608%

    No Known Activations