© 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. 7165
    Prev
    Next
    INDEX
    Explanations

    judgement or 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
    åıł
    -0.09
    ç«ĻçĿĢ
    -0.09
    æł·
    -0.09
    讳
    -0.08
    oves
    -0.08
    éĢļé£İ
    -0.08
    iger
    -0.08
    ensa
    -0.08
    åħ¸
    -0.08
    _SENS
    -0.08
    POSITIVE LOGITS
    åĪ¤æĸŃ
    0.17
    è¯Ħå®ļ
    0.13
     judgement
    0.12
     judgments
    0.12
    ç»ĵ论
    0.12
    åĪ¤å®ļ
    0.12
     judgment
    0.12
    è¯Ħä»·
    0.12
    jud
    0.11
     opinion
    0.11
    Activations Density 0.083%

    No Known Activations