© 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. 35-TRANSCODER-HP
    7. 39955
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åīįä¸ĸ
    -0.33
    ä¼¼ä¹İæĺ¯
    -0.28
    ÑģÑĤеÑĢ
    -0.27
    ä¼¼ä¹İ
    -0.27
     seems
    -0.27
    p
    -0.27
    Ups
    -0.26
    igest
    -0.26
     seem
    -0.25
    好åĥı
    -0.24
    POSITIVE LOGITS
    ml
    0.30
    keit
    0.28
    ML
    0.28
    mlx
    0.28
    меÑĢ
    0.27
    ener
    0.27
    墨
    0.27
    èĩ¾
    0.26
    ones
    0.26
    å¢ŀæ·»
    0.26
    Activations Density 2.051%

    No Known Activations