© 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. 162019
    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
     manners
    -0.27
     quickest
    -0.27
     scramble
    -0.26
    fas
    -0.26
    vote
    -0.25
    fax
    -0.24
    èµ·åĪ°äºĨ
    -0.24
    éĻħ
    -0.24
    ansen
    -0.23
     ha
    -0.23
    POSITIVE LOGITS
    '%(
    0.30
    å²ģ以ä¸ĭ
    0.28
    "%(
    0.27
    æĻļæĬ¥
    0.27
    evice
    0.25
     anmeld
    0.25
    latex
    0.25
    ¯¯¯¯
    0.24
     Hers
    0.24
     ("%
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.