© 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. 24-TRANSCODER-HP
    7. 149718
    Prev
    Next
    INDEX
    Explanations

    hyphen or slash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼ĢæĶ¯
    -0.30
    åĽĬ
    -0.26
    æħİ
    -0.26
    ä¿¡èµĸ
    -0.25
    Responder
    -0.24
    /Linux
    -0.24
     Rail
    -0.24
    æĶ¯åĩº
    -0.24
    cción
    -0.23
    å±Ģéķ¿
    -0.23
    POSITIVE LOGITS
    ements
    0.33
    ence
    0.30
    reds
    0.29
    izes
    0.28
    ences
    0.28
    ased
    0.27
    ities
    0.27
    rema
    0.27
    ses
    0.27
    lob
    0.27
    Activations Density 0.178%

    No Known Activations