© 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. 24270
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è´¸
    -0.27
    егиÑģÑĤ
    -0.26
    Ļ¶
    -0.26
     blat
    -0.26
    èªĵ
    -0.25
    æѦ
    -0.25
    èĢĥåľº
    -0.25
    缸éĤ»
    -0.25
     deltaTime
    -0.24
    Signals
    -0.24
    POSITIVE LOGITS
    cope
    0.28
    骥
    0.27
     improved
    0.24
    phere
    0.24
    丼æŀĹ
    0.24
    .Dis
    0.24
     tight
    0.24
    aldi
    0.24
    衾
    0.23
    apollo
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.