© 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. 54303
    Prev
    Next
    INDEX
    Explanations

    white + descriptors

    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
    æĻ¦
    -0.11
    秣
    -0.11
    çİ»çĴĥ
    -0.10
    æļ§
    -0.09
     Ras
    -0.09
    íľ´
    -0.09
    åĢ¾
    -0.09
    rient
    -0.09
    uther
    -0.09
    åıªä¼ļ
    -0.09
    POSITIVE LOGITS
    -white
    0.16
    çĻ½èī²çļĦ
    0.15
    white
    0.14
    çĻ½èī²
    0.14
     white
    0.13
    White
    0.13
    çĻ½
    0.13
     Whites
    0.13
    .white
    0.12
     White
    0.12
    Activations Density 0.096%

    No Known Activations