© 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. 109204
    Prev
    Next
    INDEX
    Explanations

    I

    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
    æĪij们
    -0.38
     ìļ°ë¦¬ëĬĶ
    -0.28
     exhaust
    -0.28
    大家
    -0.28
    åIJĦè¡Į
    -0.26
    åIJĦ
    -0.26
    å°½
    -0.25
    thers
    -0.24
     we
    -0.24
    ~/
    -0.24
    POSITIVE LOGITS
     trouble
    0.27
    iker
    0.26
    åĪ»
    0.24
    AGER
    0.24
    Bon
    0.24
     ÑĨен
    0.24
    cla
    0.24
     ?>>
    0.24
    ç»Ļ她
    0.23
    acon
    0.23
    Activations Density 1.008%

    No Known Activations