© 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. 25-TRANSCODER-HP
    7. 109273
    Prev
    Next
    INDEX
    Explanations

    describing a specific instance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĤ£ä¸ªæŶåĢĻ
    -0.42
    éĤ£æŶ
    -0.34
    è¿Ļ个æŶåĢĻ
    -0.33
    è¿Ļä¸Ģ天
    -0.33
    è¿ĻæŶåĢĻ
    -0.31
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.31
    éĤ£ä¸Ģ天
    -0.30
    éĤ£æŶåĢĻ
    -0.29
    éĿĴ
    -0.29
    è¿ĻæŶ
    -0.28
    POSITIVE LOGITS
    åĪ©äºļ
    0.28
    arming
    0.25
    plib
    0.24
    IONS
    0.24
     furnished
    0.24
    @update
    0.24
     whit
    0.24
    ÑģÑĤÑĢÑĥкÑĤоÑĢ
    0.23
    izers
    0.23
     qed
    0.23
    Activations Density 1.005%

    No Known Activations