© 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. 22974
    Prev
    Next
    INDEX
    Explanations

    code/technical articles

    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
     imper
    -0.27
     neg
    -0.27
     Citadel
    -0.26
    éī´åĪ«
    -0.26
     conserv
    -0.26
    emetery
    -0.26
    esco
    -0.26
    çľĭä¸įåĩº
    -0.25
    efa
    -0.25
    åĪ¤åĨ³
    -0.25
    POSITIVE LOGITS
    ram
    0.30
    æŃ¤äºº
    0.27
    ugh
    0.27
    rug
    0.26
    å¤ĩ
    0.26
    Æ¡
    0.25
    лÑģÑı
    0.25
    aldi
    0.25
    æħĮ
    0.24
     wors
    0.24
    Activations Density 0.001%

    No Known Activations