© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23866
    Prev
    Next
    INDEX
    Explanations

    temperature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    奢
    -0.29
    ence
    -0.28
     publishing
    -0.27
     przez
    -0.27
     close
    -0.26
    èĵ
    -0.25
    qui
    -0.25
     closes
    -0.25
     subscription
    -0.24
     Publishing
    -0.24
    POSITIVE LOGITS
    å¯ĴåĨ·
    0.40
    å¯ĴåĨ¬
    0.39
    ä½İ温
    0.37
    åĨ·åĨ»
    0.36
    åĨ»
    0.35
    obox
    0.32
    åĨ¬å¤©
    0.31
     Frozen
    0.29
     Cry
    0.29
     freeze
    0.29
    Activations Density 0.003%

    No Known Activations