© 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. 24458
    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
    averse
    -0.30
    BOSE
    -0.29
    imuth
    -0.28
    .ibm
    -0.27
    witter
    -0.26
    _exports
    -0.25
    éłĨ
    -0.25
    WAY
    -0.25
    way
    -0.24
     Beard
    -0.24
    POSITIVE LOGITS
    æľ¬èº«å°±æĺ¯
    0.27
    kaar
    0.27
    è½®å»ĵ
    0.27
     Trial
    0.26
     trial
    0.25
    ä¸įæĺ¯ä¸Ģ个
    0.25
    æłĩå¿Ĺ
    0.24
     Counseling
    0.23
     Purs
    0.23
    geh
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.