© 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. 23-TRANSCODER-HP
    7. 24847
    Prev
    Next
    INDEX
    Explanations

    surfing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    пон
    -0.29
    cept
    -0.27
     occ
    -0.26
    ään
    -0.26
     Was
    -0.25
    iguous
    -0.25
     traditions
    -0.25
     WAS
    -0.25
    prise
    -0.24
    Was
    -0.24
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.57
    æīĢ带æĿ¥çļĦ
    0.57
    æīĢ产çĶŁçļĦ
    0.51
    å¼ķèµ·çļĦ
    0.48
    æīĢåģļçļĦ
    0.43
    æīĢæıIJä¾ĽçļĦ
    0.41
    æıIJä¾ĽçļĦ
    0.40
    产çĶŁçļĦ
    0.39
    éĢłæĪIJçļĦ
    0.38
    æıIJåĩºçļĦ
    0.38
    Activations Density 0.003%

    No Known Activations