© 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. 24594
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
     mid
    -0.28
    æĹº
    -0.28
    ought
    -0.27
    ark
    -0.27
     commands
    -0.26
    zens
    -0.25
     voices
    -0.24
     post
    -0.24
     tapes
    -0.24
    ç§į
    -0.23
    POSITIVE LOGITS
    åıijå±ķ缮æłĩ
    0.28
    hos
    0.27
    goog
    0.27
    itionally
    0.25
    iero
    0.25
    бÑĥÑĢ
    0.25
    bstract
    0.24
    éĹ®é¢ĺæĺ¯
    0.24
    缮çļĦ
    0.24
    SOR
    0.24
    Activations Density 0.063%

    No Known Activations