© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107704
    Prev
    Next
    INDEX
    Explanations

    varied sources

    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
    kah
    -0.28
    åľĪ
    -0.26
    Rich
    -0.25
     Rich
    -0.24
    å¼·ãģĦ
    -0.24
    åĴĮ个人
    -0.23
     subtitles
    -0.23
    alendar
    -0.23
    丰å¯Įå¤ļ彩
    -0.23
    Collector
    -0.23
    POSITIVE LOGITS
    blocking
    0.30
    igli
    0.28
    arro
    0.26
    /auto
    0.26
     bureaucr
    0.25
    ething
    0.25
     emerging
    0.24
     blocking
    0.24
    ène
    0.24
     blaming
    0.24
    Activations Density 0.914%

    No Known Activations