© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17946
    Prev
    Next
    INDEX
    Explanations

    vibe or variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mente
    -0.10
    Ñģ
    -0.10
    lv
    -0.09
    ref
    -0.09
    oice
    -0.09
    ¬
    -0.08
    lld
    -0.08
    åī©
    -0.08
    ousel
    -0.08
    ¼
    -0.08
    POSITIVE LOGITS
    berman
    0.11
    lez
    0.10
    ingly
    0.10
    olare
    0.10
    ally
    0.10
    ê»ı
    0.09
    åįģ足
    0.09
    lessly
    0.09
    械
    0.09
    etically
    0.09
    Activations Density 0.002%

    No Known Activations