© 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. 18631
    Prev
    Next
    INDEX
    Explanations

    say "gy" ending

    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
    ulo
    -0.27
    embre
    -0.27
    feld
    -0.27
    rán
    -0.26
    ä¹¾åĿ¤
    -0.26
    fabs
    -0.25
     rule
    -0.25
    otine
    -0.25
    ÑĥÑĤ
    -0.25
    鼷æĸ¯
    -0.25
    POSITIVE LOGITS
    unity
    0.32
    agy
    0.31
    sse
    0.28
    ivy
    0.28
    ä¼°
    0.27
     Po
    0.27
     ag
    0.27
    ä¸į足
    0.26
    Po
    0.26
     AG
    0.25
    Activations Density 0.123%

    No Known Activations