© 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. 24651
    Prev
    Next
    INDEX
    Explanations

    antenna

    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
    jure
    -0.27
    è¿ĩåī©
    -0.26
    FTA
    -0.26
    cratch
    -0.26
    heed
    -0.26
     Ãľ
    -0.26
     pellets
    -0.25
    usalem
    -0.25
    å½ĵä¹ĭ
    -0.24
    dera
    -0.24
    POSITIVE LOGITS
    eurs
    0.30
    ç«Ļåľ¨
    0.28
    WebResponse
    0.27
    int
    0.26
    ees
    0.25
    Hide
    0.25
    linked
    0.24
    wav
    0.23
    orarily
    0.23
     recept
    0.23
    Activations Density 0.014%

    No Known Activations