© 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. 23-TRANSCODER-HP
    7. 25310
    Prev
    Next
    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹģ
    -0.29
    åĬĿ
    -0.28
    èĹ
    -0.27
    为大家
    -0.26
    endir
    -0.26
    (ra
    -0.25
    æ¼Ķ
    -0.25
    å°ijä¸įäºĨ
    -0.24
    åĩ¡
    -0.24
    è¦ģæ±Ĥ
    -0.24
    POSITIVE LOGITS
    ulses
    0.26
    åĨįæĿ¥
    0.25
     RESERVED
    0.25
    æŁ¥çľĭæĽ´å¤ļ
    0.25
     ][
    0.24
    oren
    0.24
    bara
    0.23
     Hans
    0.23
     Toolkit
    0.23
     Clause
    0.23
    Activations Density 0.004%

    No Known Activations