© 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. 40193
    Prev
    Next
    INDEX
    Explanations

    0

    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
    IEWS
    -0.31
    æĪij们
    -0.27
    å¸ĮæľĽ
    -0.26
    ä»ĸçļĦ
    -0.26
    çħ§
    -0.26
    使çĶ¨çļĦ
    -0.26
     оÑģобенно
    -0.26
    =output
    -0.25
    æĬĢ
    -0.24
    使çĶ¨
    -0.24
    POSITIVE LOGITS
     to
    0.40
     mm
    0.29
     Feinstein
    0.28
    ller
    0.28
     nm
    0.28
    ckt
    0.27
     ln
    0.27
    bsp
    0.27
     rms
    0.26
    lt
    0.25
    Activations Density 11.961%

    No Known Activations