© 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. 64036
    Prev
    Next
    INDEX
    Explanations

    scientific research/documentation

    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
    好人
    -0.28
    ocular
    -0.27
     rounds
    -0.27
     rop
    -0.27
    橹
    -0.26
    ihan
    -0.26
    æŃ£ä¹ī
    -0.25
     ÑģÑĤÑĢаÑħов
    -0.25
    lob
    -0.25
    çĻĮ
    -0.24
    POSITIVE LOGITS
    eth
    0.27
    mith
    0.27
    æĻ¾
    0.26
    herits
    0.26
    ä¸Ģä¸ĸ
    0.25
    cies
    0.25
    ä¸įç¡®å®ļ
    0.25
     principals
    0.24
    çļĦæĢģ度
    0.24
    ightly
    0.24
    Activations Density 1.269%

    No Known Activations