© 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. 22-TRANSCODER-HP
    7. 98420
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иÑĤелÑĮно
    -0.30
     Loaded
    -0.29
     (--
    -0.26
    åħ·æľīä¸Ģå®ļ
    -0.26
    Loaded
    -0.25
    åı£æ°Ķ
    -0.24
    imized
    -0.24
    JA
    -0.24
    Insensitive
    -0.23
    igon
    -0.23
    POSITIVE LOGITS
    ä¸įæĸŃåĪĽæĸ°
    0.28
    csr
    0.27
    lemn
    0.24
    vip
    0.24
    cie
    0.24
    ÃŁen
    0.24
    GMT
    0.23
    TestCase
    0.23
     Cyr
    0.23
    åĬĽäºī
    0.23
    Activations Density 0.007%

    No Known Activations