© 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. 12-TRANSCODER-HP
    7. 22955
    Prev
    Next
    INDEX
    Explanations

    Classical, Renaissance art/music

    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
    ropy
    -0.30
    .codehaus
    -0.27
    ISTER
    -0.26
    Whole
    -0.25
    gio
    -0.25
    ARIO
    -0.25
    åħ¨ä½ĵ
    -0.24
    å®Ļ
    -0.23
    onymous
    -0.23
    (IService
    -0.23
    POSITIVE LOGITS
     further
    0.28
    flu
    0.27
     conditions
    0.27
     flu
    0.26
    äºĴåĬ©
    0.25
     Conditions
    0.25
     fick
    0.25
     moll
    0.25
     influence
    0.25
     wa
    0.25
    Activations Density 0.001%

    No Known Activations