© 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. 149841
    Prev
    Next
    INDEX
    Explanations

    technical reviews/documentation

    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
     itch
    -0.28
     jog
    -0.27
    aber
    -0.25
     berries
    -0.24
    berry
    -0.24
    OPSIS
    -0.24
    arda
    -0.23
    éĢħ
    -0.23
    [Unit
    -0.23
    dojo
    -0.23
    POSITIVE LOGITS
    ower
    0.27
    IMS
    0.26
     toler
    0.26
    Eigen
    0.25
    isol
    0.25
     clang
    0.25
    æ¹ĸåĮº
    0.25
     Eigen
    0.24
    å®ĮæĪIJäºĨ
    0.24
    asts
    0.24
    Activations Density 0.896%

    No Known Activations