© 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. 31-TRANSCODER-HP
    7. 19467
    Prev
    Next
    INDEX
    Explanations

    say ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iances
    -0.31
    ä¸ĢçĻ¾å¤ļ
    -0.30
    paged
    -0.27
    oment
    -0.26
     vá»įng
    -0.25
     taped
    -0.25
    çĶ·ç¥ŀ
    -0.23
     cargar
    -0.23
    perms
    -0.23
    Sibling
    -0.23
    POSITIVE LOGITS
    herits
    0.30
    WR
    0.25
    ewis
    0.25
    adro
    0.25
     Wat
    0.25
    inidad
    0.25
    éħ¸
    0.24
    ä¸īä½įä¸Ģä½ĵ
    0.24
    æıIJ
    0.24
    éĻį
    0.23
    Activations Density 0.115%

    No Known Activations