© 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. 107899
    Prev
    Next
    INDEX
    Explanations

    ink

    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
     details
    -0.31
     assets
    -0.31
     protocols
    -0.30
     outcomes
    -0.30
     endpoints
    -0.29
     entries
    -0.29
     points
    -0.28
     quotations
    -0.28
     queries
    -0.28
     tickets
    -0.28
    POSITIVE LOGITS
    å¿ĥ仪
    0.29
    空åīį
    0.29
    被èªī
    0.27
    åīįæīĢæľª
    0.27
    两æĿ¡
    0.27
    oteric
    0.26
    çIJĨåıij
    0.26
    ä¸įéĶĻçļĦ
    0.25
    rador
    0.25
    odelist
    0.25
    Activations Density 0.986%

    No Known Activations