© 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. 51578
    Prev
    Next
    INDEX
    Explanations

    of [word]

    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
    orian
    -0.09
    groupId
    -0.09
    çĭ¬
    -0.08
    ibilit
    -0.08
     Rope
    -0.08
    æĹłç¼ĺ
    -0.08
    utc
    -0.08
    ÙĥÙĬ
    -0.08
    	tb
    -0.08
    .GetResponse
    -0.08
    POSITIVE LOGITS
    åĩºå¤Ħ
    0.10
    entifier
    0.10
    åĪĩåħ¥çĤ¹
    0.10
    quil
    0.09
    çªģçł´åı£
    0.09
     key
    0.09
    olean
    0.09
    çļĦåħ³éĶ®
    0.09
    涮
    0.09
    åħ³éĶ®
    0.09
    Activations Density 0.155%

    No Known Activations