© 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. 32-TRANSCODER-HP
    7. 41334
    Prev
    Next
    INDEX
    Explanations

    say number 2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİŁæĸĩåľ°åĿĢ
    -0.29
    atism
    -0.25
     middle
    -0.25
     conver
    -0.24
    æ§Ĭ
    -0.23
    irement
    -0.23
    batim
    -0.23
     planet
    -0.23
     resp
    -0.23
    irk
    -0.23
    POSITIVE LOGITS
    两æĿ¡
    0.33
    æľĿ
    0.32
    两个
    0.31
    åı·
    0.31
    两åıª
    0.31
    两çĤ¹
    0.29
    两ç§į
    0.28
    两大
    0.27
    berger
    0.26
    zon
    0.25
    Activations Density 0.009%

    No Known Activations