© 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. 107931
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    æįı
    -0.29
    ä¸ĢéŨ
    -0.28
    说
    -0.25
    orative
    -0.24
     joe
    -0.24
    inflate
    -0.24
    horia
    -0.24
    æĻ¦
    -0.23
    ä¸Ģå¹´
    -0.23
     toc
    -0.23
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.32
     other
    0.30
    åħ¶ä»ĸ
    0.29
     Other
    0.28
    åı¦ä¸Ģä½į
    0.28
     others
    0.28
    other
    0.27
    主
    0.27
    åı¦ä¸Ģ
    0.27
    åħ¶ä»ĸçļĦ
    0.27
    Activations Density 0.909%

    No Known Activations