© 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. 9102
    Prev
    Next
    INDEX
    Explanations

    Jose followed by name

    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
    å°¼äºļ
    -0.09
    aley
    -0.09
    ÑĢод
    -0.09
    èijŃ
    -0.09
    itt
    -0.09
    ãģĤãģ£ãģŁ
    -0.09
    .localization
    -0.08
    ORD
    -0.08
    ä¸Ńéĵģ
    -0.08
    ãģľ
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.10
    ogram
    0.09
    liness
    0.09
    æĺ¥å¤©
    0.09
    çľ¼åħī
    0.09
    ÙĪع
    0.09
    udio
    0.09
    oft
    0.09
    curity
    0.08
    好å¤Ħ
    0.08
    Activations Density 0.010%

    No Known Activations