© 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. 9076
    Prev
    Next
    INDEX
    Explanations

    cider house

    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
    çĿĽ
    -0.11
    yen
    -0.10
    aters
    -0.09
    é²Ķ
    -0.09
    å¿¡
    -0.09
    饰
    -0.09
    riad
    -0.09
    äºĨä¸Ģæī¹
    -0.09
    æĹı
    -0.09
    INO
    -0.09
    POSITIVE LOGITS
    çīĿ
    0.10
    0.10
     vinegar
    0.09
    ENTITY
    0.09
    é¦Ĩ
    0.09
    ftware
    0.08
    æ·ĺæ±°
    0.08
    stone
    0.08
    涧
    0.08
    çī¡
    0.08
    Activations Density 0.004%

    No Known Activations