© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36067
    Prev
    Next
    INDEX
    Explanations

    fluent English

    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
    OrUpdate
    -0.11
    æĢ¥äºİ
    -0.10
    大æĪ·
    -0.09
    acle
    -0.09
    ifu
    -0.09
    ervation
    -0.08
    lijke
    -0.08
    Invariant
    -0.08
     wen
    -0.08
    .managed
    -0.08
    POSITIVE LOGITS
    åĨįéĢł
    0.10
    åİķ
    0.10
    æµģçķħ
    0.10
    çĺ¸
    0.10
    ä¸įéĢļ
    0.09
    ä¸įæ¸ħ
    0.09
    vo
    0.09
    ç¼Ń
    0.09
    ç»ıçIJĨ
    0.09
    ä¸ĸ代
    0.08
    Activations Density 0.012%

    No Known Activations