© 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. 37082
    Prev
    Next
    INDEX
    Explanations

    niche

    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
    ance
    -0.10
    den
    -0.10
    ains
    -0.09
    apo
    -0.08
    di
    -0.08
    箸
    -0.08
    æ±Ĺ
    -0.08
    sWith
    -0.08
    åħħæ²Ľ
    -0.07
    秽
    -0.07
    POSITIVE LOGITS
    ellaneous
    0.13
     nich
    0.11
    åĤ¬
    0.10
    èĢĻ
    0.10
    ä¹ĭä½ľ
    0.10
    å¨ħ
    0.10
    人士
    0.10
    åŃIJéĩĮ
    0.10
    assin
    0.10
    ä¹ĭåĨħ
    0.10
    Activations Density 0.008%

    No Known Activations