© 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. 108205
    Prev
    Next
    INDEX
    Explanations

    Titles and names

    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
    åī¯æľ¬
    -0.25
    -multi
    -0.25
     area
    -0.24
    ä¸įåħį
    -0.24
    berra
    -0.24
     AREA
    -0.23
    apia
    -0.23
    "\↵
    -0.23
     ë©
    -0.23
    ibia
    -0.23
    POSITIVE LOGITS
     ale
    0.27
    èķī
    0.27
    使ä¹ĭ
    0.26
    ä¹ĭåIJİ
    0.25
    PEC
    0.25
     Thomson
    0.24
     Ale
    0.24
     gm
    0.24
    é¹ij
    0.23
    pressions
    0.23
    Activations Density 0.896%

    No Known Activations