© 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. 18420
    Prev
    Next
    INDEX
    Explanations

    Okanagan, Poughkeepsie, Ponte Vista

    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
    oller
    -0.10
    ç³ł
    -0.10
    饥
    -0.09
    precision
    -0.08
    ìķĻ
    -0.08
    .hit
    -0.08
    avers
    -0.08
    æ¤Ĵ
    -0.08
    åIJĪæĪIJ
    -0.08
     kè
    -0.08
    POSITIVE LOGITS
    寰
    0.10
    éĿ¢ç§¯çº¦
    0.09
    管çIJĨéĥ¨éŨ
    0.09
    otine
    0.09
    ogle
    0.09
    åĢŁåı£
    0.09
    äºĭçī©
    0.09
     Beste
    0.09
    smouth
    0.08
    orro
    0.08
    Activations Density 0.002%

    No Known Activations