© 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. 23-TRANSCODER-HP
    7. 24588
    Prev
    Next
    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catch
    -0.27
     catch
    -0.27
    hots
    -0.27
    alties
    -0.25
    åĭ¾
    -0.24
    è°ª
    -0.24
    uct
    -0.24
    çªģçł´åı£
    -0.24
    ProcessEvent
    -0.23
    æļĤ
    -0.23
    POSITIVE LOGITS
     Rental
    0.28
    oster
    0.27
    好åIJĹ
    0.26
    人çī©
    0.25
    arna
    0.24
    arah
    0.24
    æĸĩçĮ®
    0.24
    麹
    0.23
    ä»Ģä¹ĪæĦıæĢĿ
    0.23
    çİ®
    0.23
    Activations Density 0.088%

    No Known Activations