© 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. 7706
    Prev
    Next
    INDEX
    Explanations

    fingers

    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
    çĶ¨æīĭ
    -0.11
    æĸ§
    -0.10
    è¦ģçĶ¨
    -0.09
    å·½
    -0.08
    ocs
    -0.08
    个çĻ¾åĪĨ
    -0.08
    æ³Ħ
    -0.08
    ãģij
    -0.08
    å·²äºİ
    -0.08
    ÙĤاد
    -0.08
    POSITIVE LOGITS
    æįº
    0.10
    ä¸Ĭç½ij
    0.10
    âģ½
    0.09
    bon
    0.09
    ç¿ĺ
    0.09
    ials
    0.08
    tok
    0.08
    ä¼°
    0.08
    å°±èĥ½å¤Ł
    0.08
    Cascade
    0.08
    Activations Density 0.011%

    No Known Activations