© 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. 108064
    Prev
    Next
    INDEX
    Explanations

    code snippets and foreign languages

    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
    omers
    -0.27
    compound
    -0.26
     compound
    -0.26
     herr
    -0.26
    fan
    -0.26
    éĵ¾æĿ¡
    -0.26
    æī¹æ¬¡
    -0.24
     hom
    -0.24
     ferr
    -0.24
    omer
    -0.24
    POSITIVE LOGITS
    åľ°ä¸ĭ室
    0.27
    buch
    0.25
     fortunes
    0.25
     addObject
    0.25
    ISTIC
    0.25
    ä»·éĴ±
    0.24
    æ±Ŀ
    0.24
    ÑĢо
    0.24
    {:
    0.24
    rys
    0.24
    Activations Density 0.511%

    No Known Activations