© 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. 22878
    Prev
    Next
    INDEX
    Explanations

    rock and roll

    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
    æŁĶ
    -0.26
    CharacterSet
    -0.25
    anged
    -0.25
    à¸Ĭà¸Ńà¸ļ
    -0.24
    Got
    -0.24
    addAction
    -0.24
    -top
    -0.24
    em
    -0.24
    æİĴè¡Įæ¦ľ
    -0.24
    ech
    -0.23
    POSITIVE LOGITS
    éĦĹ
    0.27
    braska
    0.27
     Shan
    0.26
    åľ¨åIJĮä¸Ģ
    0.26
    æ±²
    0.26
    çĺ¿
    0.25
     Assertion
    0.25
    caffold
    0.24
    ck
    0.24
     constexpr
    0.24
    Activations Density 0.001%

    No Known Activations