© 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. 149969
    Prev
    Next
    INDEX
    Explanations

    review

    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
    DIRECTORY
    -0.25
    апÑĢ
    -0.25
    perms
    -0.24
    ä¸įæĪIJ
    -0.24
    -Jul
    -0.24
    åħ¶æ¬¡æĺ¯
    -0.24
    ä¸įåIJĮç¨ĭ度
    -0.24
     Britann
    -0.23
    év
    -0.23
    nü
    -0.23
    POSITIVE LOGITS
    Valid
    0.28
     validity
    0.27
    setup
    0.27
    ting
    0.26
    able
    0.26
    ist
    0.25
    spath
    0.25
    riority
    0.24
     dialog
    0.24
     Valid
    0.24
    Activations Density 1.323%

    No Known Activations