© 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. 35-TRANSCODER-HP
    7. 40189
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģç§į
    -0.29
     Px
    -0.28
     itself
    -0.28
    ä¸Ģ件äºĭ
    -0.27
    ä¸ĢåĪĩ
    -0.25
    ATOR
    -0.25
    SOR
    -0.25
    алÑĮ
    -0.24
    ä¼łå¯¼
    -0.24
    éĵİ
    -0.24
    POSITIVE LOGITS
    hab
    0.26
    personal
    0.25
     unrelated
    0.25
     pricey
    0.24
    grad
    0.24
     dri
    0.24
    .EntityManager
    0.24
    fried
    0.23
    legalArgumentException
    0.23
    -middle
    0.23
    Activations Density 12.327%

    No Known Activations