© 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. 53280
    Prev
    Next
    INDEX
    Explanations

    expectation question

    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
    ä½Ĩä¹Ł
    -0.10
    çĶ³ãģĹ
    -0.09
    TRACT
    -0.09
    ä½Ĩåį´
    -0.08
    nero
    -0.08
    åĪĴ
    -0.08
    åį³ä½¿æĺ¯
    -0.08
     endwhile
    -0.08
    åį´æĺ¯
    -0.08
    è£ħéħį
    -0.08
    POSITIVE LOGITS
    åijĹ
    0.12
    ниÑĩ
    0.10
    举
    0.10
    å½ĵçĦ¶æĺ¯
    0.10
    è°¢éĤĢ
    0.09
    è§Ħ模æľĢ大
    0.09
    oki
    0.09
    ä»¥ä¹łè¿ijå¹³
    0.09
    åģļ强
    0.09
    aven
    0.08
    Activations Density 0.119%

    No Known Activations