© 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. 20826
    Prev
    Next
    INDEX
    Explanations

    small molecules and compounds

    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
    dge
    -0.10
    гÑĢан
    -0.09
    umph
    -0.09
    aupt
    -0.09
    ssid
    -0.09
    ì²ŃìĨĮ
    -0.09
    ectl
    -0.09
    _OPERATOR
    -0.08
    æ¼ī
    -0.08
    ControlItem
    -0.08
    POSITIVE LOGITS
    对æĬĹ
    0.09
    åħĪ导
    0.09
    èį¯çī©
    0.09
    èĢĨ
    0.09
    èĿ¶
    0.08
    ä¸ĩ象
    0.08
    oids
    0.08
     ÑĦл
    0.08
    騰
    0.08
    追寻
    0.08
    Activations Density 0.666%

    No Known Activations