© 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. 18953
    Prev
    Next
    INDEX
    Explanations

    global disease statistics

    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
     ÑģÑĤÑĢаÑħов
    -0.28
     addTarget
    -0.27
    vant
    -0.27
     NodeType
    -0.26
    iya
    -0.25
    éļ¾åıĹ
    -0.25
    aring
    -0.25
    stre
    -0.25
    çħİ
    -0.24
     cá
    -0.24
    POSITIVE LOGITS
    global
    0.39
    åħ¨çIJĥ
    0.35
     global
    0.34
    ILLA
    0.31
    Global
    0.31
     Global
    0.30
     GLOBAL
    0.29
    GLOBAL
    0.29
    fg
    0.27
     worldwide
    0.27
    Activations Density 0.037%

    No Known Activations