© 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
    2. Qwen3-4B
    3. 35-TRANSCODER-HP
    4. 39989
    Prev
    Next
    INDEX
    Explanations

    O or C

    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
    å§Ķ
    -0.27
    ipse
    -0.25
     v
    -0.25
    è¿Ļ次
    -0.24
    clar
    -0.23
    dom
    -0.23
     ÑģобÑģÑĤвенно
    -0.23
    iv
    -0.23
    æĶĢåįĩ
    -0.23
    ClassName
    -0.23
    POSITIVE LOGITS
    inema
    0.27
    稳
    0.25
     typealias
    0.24
    inant
    0.24
    âĨ©
    0.24
    cheme
    0.24
    è°Ģ
    0.24
     pomp
    0.24
    itta
    0.23
     amat
    0.23
    Activations Density 0.953%

    No Known Activations