© 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. 27-TRANSCODER-HP
    7. 58111
    Prev
    Next
    INDEX
    Explanations

    Scientific proving/disproving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢæĶ¯
    -0.28
    nde
    -0.27
    lox
    -0.26
    ativa
    -0.25
    ubb
    -0.24
    è¿ĻæĶ¯
    -0.24
    endir
    -0.24
    Vault
    -0.24
    å®ĥ
    -0.23
    illery
    -0.23
    POSITIVE LOGITS
    ç§ijåѦ
    0.38
    ç§ijåѸ
    0.30
     scientific
    0.28
    潺
    0.27
    istes
    0.27
    ê³¼íķĻ
    0.26
     scientifically
    0.26
    æĺ¾ç¤ºåĩº
    0.25
    IPA
    0.24
     guessing
    0.24
    Activations Density 0.004%

    No Known Activations