© 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. 149470
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     rules
    -0.29
    åİī
    -0.28
    æ£ĢéªĮ
    -0.27
    åį§
    -0.27
     memes
    -0.26
     tab
    -0.26
     encount
    -0.26
    è§ĦåĪĻ
    -0.26
    为æѤ
    -0.25
    ornings
    -0.24
    POSITIVE LOGITS
    æĬĹæ°§åĮĸ
    0.30
    +xml
    0.28
    éĵħ
    0.27
    ioxid
    0.27
    æĪijä»¬çŁ¥éģĵ
    0.27
     cream
    0.26
    immune
    0.25
    cream
    0.25
     oxidative
    0.25
    coli
    0.24
    Activations Density 0.903%

    No Known Activations