© 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. 107320
    Prev
    Next
    INDEX
    Explanations

    questions, confusion

    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
     mise
    -0.27
    车åĨħ
    -0.25
    è·Łä¸įä¸Ĭ
    -0.25
    两个人
    -0.25
    åı¦ä¸ĢåįĬ
    -0.24
    éĽį
    -0.24
    неÑĢ
    -0.24
    arde
    -0.24
    ä¸įåıĺ
    -0.24
    à¹Ģà¸Ĺศ
    -0.24
    POSITIVE LOGITS
     pitches
    0.26
    -sdk
    0.25
     Cin
    0.25
    imson
    0.25
     oct
    0.25
     nearest
    0.24
     noqa
    0.24
     pitched
    0.24
     pitch
    0.24
     realms
    0.23
    Activations Density 27.144%

    No Known Activations