© 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. 24708
    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
    books
    -0.24
    profiles
    -0.24
    onom
    -0.24
    å»ĵ
    -0.24
     taxable
    -0.24
    æŶæĬ¥
    -0.24
    akter
    -0.23
    è°±
    -0.23
    UPI
    -0.23
    odial
    -0.23
    POSITIVE LOGITS
    elsing
    0.27
     ÑģÑĤеп
    0.26
     Fore
    0.24
    кÑĢа
    0.24
    ÉĻ
    0.24
    èĬ¬
    0.23
    cono
    0.23
    fieldset
    0.23
    åĥ°
    0.23
     exporting
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.