© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7847
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers

    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
     XK
    -0.10
    ovation
    -0.09
    ç¥ļ
    -0.09
    alaria
    -0.08
    æķ¦
    -0.08
    èŀ½
    -0.08
    åŀĥåľ¾åĪĨç±»
    -0.08
    èĬ±çĵ£
    -0.08
    sei
    -0.08
    ãĤīãģļ
    -0.08
    POSITIVE LOGITS
    以æĿ¥
    0.11
    æĹ¶æľŁçļĦ
    0.09
    hood
    0.09
    -era
    0.09
    æĹ¶æľŁ
    0.09
    åģļçļĦäºĭ
    0.09
    åĦŁ
    0.09
    жÑĥ
    0.09
    å½¢æĪIJçļĦ
    0.09
    IMER
    0.09
    Activations Density 0.142%

    No Known Activations