© 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. 130018
    Prev
    Next
    INDEX
    Explanations

    Place/organization names, descriptions

    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
    äºŃ
    -0.25
    ASF
    -0.25
     {%
    -0.25
    ÑĩаÑĤ
    -0.25
     amo
    -0.24
    滩
    -0.24
    lá
    -0.24
     Caption
    -0.23
    eled
    -0.23
    ħį
    -0.23
    POSITIVE LOGITS
     primaries
    0.31
    imiter
    0.28
    ä¸įçŁ¥
    0.27
    å¤ļåįĬ
    0.27
    ongan
    0.26
     pione
    0.26
    oya
    0.26
    -offs
    0.26
    subcategory
    0.25
    idental
    0.25
    Activations Density 7.822%

    No Known Activations