© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54682
    Prev
    Next
    INDEX
    Explanations

    belief and opinion

    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
    -padding
    -0.09
    åĬł
    -0.08
    ÙģÙĪر
    -0.08
    éģIJ
    -0.08
    èĬĤ
    -0.08
    liqu
    -0.08
    æ¹Ħ
    -0.08
    ä¸įåħ¬å¹³
    -0.07
    æī³
    -0.07
    _HAVE
    -0.07
    POSITIVE LOGITS
    ä¸»å¼ł
    0.13
    èªįçĤº
    0.12
    认为
    0.11
    éĥ½è®¤ä¸º
    0.11
    )view
    0.11
    -confirm
    0.10
    åĶ¯
    0.10
    æī¿è®¤
    0.10
    è¾ĺ
    0.10
    ÑģÑĥ
    0.10
    Activations Density 0.084%

    No Known Activations