© 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. 33-TRANSCODER-HP
    7. 52560
    Prev
    Next
    INDEX
    Explanations

    chair

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ãģĵãģ¨ãģ«
    -0.28
    RenderingContext
    -0.27
    åķĨä¼ļ
    -0.26
     motorcycles
    -0.25
    -Americans
    -0.25
    boys
    -0.25
     Documentary
    -0.25
    -man
    -0.24
    çĶ¨æĪ·æıIJä¾Ľ
    -0.24
    _DOC
    -0.24
    POSITIVE LOGITS
     isp
    0.32
    UA
    0.29
    大èĩªçĦ¶
    0.28
    lp
    0.28
    FFE
    0.28
    æ®Ĩ
    0.26
    çļĦç»ıåħ¸
    0.25
    ISP
    0.25
    èķ¾
    0.25
    LOGGER
    0.24
    Activations Density 0.015%

    No Known Activations