© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149480
    Prev
    Next
    INDEX
    Explanations

    in

    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
     pursuing
    -0.26
     pla
    -0.25
    çī¹æ®ĬæĥħåĨµ
    -0.25
    lin
    -0.25
    ariate
    -0.24
    urger
    -0.24
    对å¾ħ
    -0.23
    ego
    -0.23
     Nets
    -0.23
    liner
    -0.23
    POSITIVE LOGITS
    缸éĢļ
    0.28
    alth
    0.27
    compat
    0.27
    è¡¥åģ¿
    0.26
    è´§å¸ģ
    0.26
    ált
    0.24
     اÙĦÙĤØ·
    0.24
    =?
    0.24
    æ°ĽåĽ´
    0.24
    çļĦçĶ»éĿ¢
    0.24
    Activations Density 0.892%

    No Known Activations