© 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. 107544
    Prev
    Next
    INDEX
    Explanations

    ins

    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
    éĺ´
    -0.25
    å¸ĪäºĭåĬ¡æīĢ
    -0.25
    cope
    -0.24
    æĭĪ
    -0.24
    dü
    -0.24
    cape
    -0.24
    笤
    -0.24
    çĹĴ
    -0.23
    iler
    -0.23
    åijĬè¯īä½ł
    -0.23
    POSITIVE LOGITS
     extended
    0.27
    å°Ŀ
    0.26
    plevel
    0.24
     storefront
    0.24
    ä¸ĬéŨ
    0.23
    顺
    0.23
    .go
    0.23
    essen
    0.23
    apol
    0.23
    梯
    0.23
    Activations Density 0.018%

    No Known Activations