© 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. 18701
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ires
    -0.30
    iqu
    -0.29
    ilog
    -0.28
    ç¡«
    -0.28
     beh
    -0.26
    æķĪçİĩ
    -0.26
    BUR
    -0.26
    ioxide
    -0.24
    ider
    -0.24
    uhe
    -0.24
    POSITIVE LOGITS
     tÃł
    0.33
    ople
    0.31
    æĭį
    0.26
    otos
    0.25
    çŃ¹
    0.25
    ahl
    0.25
    æĭįæĭį
    0.25
    æİĴéĺŁ
    0.24
    馨
    0.24
    andler
    0.24
    Activations Density 0.006%

    No Known Activations