© 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. 52357
    Prev
    Next
    INDEX
    Explanations

    is of the 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
    ctest
    -0.08
    çŃ·åŃIJ
    -0.08
    å¤Ħå¤Ħ
    -0.08
     Ging
    -0.08
    沧æ¡ij
    -0.08
     Ded
    -0.08
     chap
    -0.08
    ç«ł
    -0.08
    èĻļ空
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.07
    POSITIVE LOGITS
    认为
    0.34
    以为
    0.26
    èªįçĤº
    0.26
    以çĤº
    0.23
    éĥ½è®¤ä¸º
    0.22
     believe
    0.21
    çĽ¸ä¿¡
    0.20
     believing
    0.20
     belief
    0.20
    è§īå¾Ĺ
    0.19
    Activations Density 0.133%

    No Known Activations