© 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. 107265
    Prev
    Next
    INDEX
    Explanations

    Proper names/code

    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
    éģĵ
    -0.33
    åĸĦ
    -0.27
    ç»Ĩ
    -0.27
     Jad
    -0.26
    éĿ¢åIJij
    -0.25
    æµģæ°´
    -0.24
    åīįåĪĹ
    -0.24
    ç»ĨåĪĨ
    -0.24
    etail
    -0.24
    å°½éĩı
    -0.24
    POSITIVE LOGITS
    noch
    0.27
    iben
    0.26
    igham
    0.25
    ookie
    0.25
    othermal
    0.25
     thumbs
    0.24
    band
    0.24
    intptr
    0.24
    hn
    0.24
     fucks
    0.23
    Activations Density 0.059%

    No Known Activations