© 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. 53444
    Prev
    Next
    INDEX
    Explanations

    leukemia

    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
    _DECL
    -0.10
    è¹¼
    -0.09
    ssi
    -0.09
     Ott
    -0.09
    è¦ģçĤ¹
    -0.09
    趸
    -0.09
    atto
    -0.09
    éļıå¤Ħ
    -0.08
    Ĥæķ°
    -0.08
     Magn
    -0.08
    POSITIVE LOGITS
     Abr
    0.09
    æĪIJè´¥
    0.09
    æ´ĹåĩĢ
    0.09
    ish
    0.08
    çĻ¾äº¿
    0.08
     ngân
    0.08
    ãģ®ãģĮ
    0.08
    æĻ°
    0.08
    éĢłè¡Ģ
    0.08
    ipt
    0.08
    Activations Density 0.153%

    No Known Activations