© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161901
    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
    ossil
    -0.26
     nonetheless
    -0.24
    çŀ½
    -0.24
    æĸĩç§ij
    -0.23
     static
    -0.23
     phá»iji
    -0.23
    uos
    -0.23
    ocal
    -0.23
     however
    -0.23
    æ»Ĥ
    -0.23
    POSITIVE LOGITS
    chin
    0.27
    æ³Ľ
    0.27
    )<<
    0.27
    ASON
    0.26
    满足
    0.26
    atisfied
    0.25
    æľĢåIJĪéĢĤ
    0.25
    "<
    0.25
    ç½²
    0.24
    éĢĤå®ľ
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.