© 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. 22954
    Prev
    Next
    INDEX
    Explanations

    Apple Inc. or .com copyright

    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
    åIJĬ
    -0.09
    å½Ĵ
    -0.08
    orer
    -0.08
     LOL
    -0.08
    è®©æĽ´å¤ļ
    -0.08
    åĮĸåIJĪçī©
    -0.08
     Crane
    -0.08
    lam
    -0.08
    Kit
    -0.08
    linger
    -0.08
    POSITIVE LOGITS
    ä¸įç»ıæĦı
    0.10
     Ride
    0.10
    éĿ¢åħ·
    0.09
    æģ¯
    0.09
    .JsonIgnore
    0.09
    ä»»æķĻ
    0.09
    éĻ¬
    0.09
    讵
    0.09
    erson
    0.08
    STRUCTOR
    0.08
    Activations Density 0.014%

    No Known Activations