© 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. 22-TRANSCODER-HP
    7. 97589
    Prev
    Next
    INDEX
    Explanations

    state of transition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°½
    -0.27
    壯
    -0.26
    浩
    -0.25
    OFF
    -0.25
     Booster
    -0.25
     uur
    -0.24
    czy
    -0.24
    -off
    -0.24
    ()"↵
    -0.24
    ()>↵
    -0.23
    POSITIVE LOGITS
    ogram
    0.29
    ï¼Į
    0.26
    iry
    0.26
    å®ĥåı¯ä»¥
    0.26
    çī¹åĪ«å£°æĺİ
    0.24
    æĿĵ
    0.24
     attendance
    0.23
    ,
    0.23
    ï¼Įåľ¨
    0.23
    odia
    0.23
    Activations Density 0.017%

    No Known Activations