© 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. 149763
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    anas
    -0.30
    credits
    -0.29
    pine
    -0.26
    бл
    -0.26
    icas
    -0.25
    .Expression
    -0.25
    own
    -0.25
    amina
    -0.24
    eder
    -0.24
    AdminController
    -0.23
    POSITIVE LOGITS
    èĬĥ
    0.26
    yers
    0.26
     Cartoon
    0.25
    è¯ķé¢ĺ
    0.25
    udad
    0.25
    _categorical
    0.25
    ä¸įè¿ľ
    0.25
    æĻ¯å¾·
    0.24
    ä¸ĵ
    0.24
    ishly
    0.24
    Activations Density 0.943%

    No Known Activations

    This feature has no known activations.