© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    mutant, double mutant, triple mutant

    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
    IFIC
    -0.09
    rear
    -0.09
    æĮ¯åħ´
    -0.09
    chas
    -0.09
     SOUR
    -0.09
    åħ¼
    -0.09
     Pul
    -0.09
    _DT
    -0.09
    dsl
    -0.09
    碧
    -0.08
    POSITIVE LOGITS
     Stam
    0.10
    éĥ½ä¸įèĥ½
    0.09
    åģļä¸įåĪ°
    0.09
    pret
    0.09
    ä¹ĭ人
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    缺失
    0.09
    åĬŁèĥ½
    0.08
    缺éĻ·
    0.08
    ä¹Łä¸įæķ¢
    0.08
    Activations Density 0.608%

    No Known Activations