© 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. 23640
    Prev
    Next
    INDEX
    Explanations

    you

    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
    åĩºè·¯
    -0.26
    ripp
    -0.25
     lå
    -0.24
    è¿Ļ段
    -0.24
    æ³ķå®Ŀ
    -0.24
    ÑģÑĤÑĢ
    -0.23
    åĶ¯ä¸Ģ
    -0.23
     fore
    -0.23
    abe
    -0.23
    STR
    -0.23
    POSITIVE LOGITS
    ctors
    0.26
    ightly
    0.25
    .esp
    0.24
    aksi
    0.24
    AAD
    0.23
    multi
    0.23
    计ç®ĹåĻ¨
    0.23
     Mesa
    0.23
    æ¯ķç«Ł
    0.23
    æĭĪ
    0.23
    Activations Density 0.000%

    No Known Activations