© 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. 24-TRANSCODER-HP
    7. 149992
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµĦ产éĩįç»Ħ
    -0.27
    '](
    -0.27
    earing
    -0.27
    atab
    -0.25
    æĪIJéķ¿ä¸º
    -0.25
    oom
    -0.24
    ub
    -0.24
    ä¼ļè§īå¾Ĺ
    -0.24
    //'
    -0.24
    å°Ĭéĩį
    -0.24
    POSITIVE LOGITS
    äºĪ以
    0.31
    å¾Ĺ以
    0.28
    为ä¹ĭ
    0.28
    ãĤĴåıĸãĤĬ
    0.27
     pro
    0.25
    åĬłä»¥
    0.25
    ÑĨев
    0.24
     prem
    0.24
    åħ¨èĥ½
    0.24
    æıIJèµ·
    0.24
    Activations Density 0.935%

    No Known Activations