© 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. 151114
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    iverse
    -0.28
     inclusive
    -0.27
    举起
    -0.26
     Reasons
    -0.25
    yme
    -0.25
     Whip
    -0.25
     reasons
    -0.25
    ters
    -0.25
    豸
    -0.24
     Äijạo
    -0.24
    POSITIVE LOGITS
    追踪
    0.30
    ä¾ĭè¡Į
    0.30
    æĻ®éĢļ人
    0.29
    æ£Ģæµĭ
    0.29
     unnoticed
    0.28
     detect
    0.28
    注æĦıåĪ°
    0.28
    åıijè§ī
    0.28
    åıijçİ°éĹ®é¢ĺ
    0.27
    åıijçİ°
    0.27
    Activations Density 0.958%

    No Known Activations