© 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. 51229
    Prev
    Next
    INDEX
    Explanations

    incline, slope, ramp

    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
     dia
    -0.10
    鼷
    -0.10
    ç²±
    -0.10
    èĦĨ
    -0.10
    èĽ¤
    -0.10
    ç¨ļ
    -0.10
    éł
    -0.10
    责任ç¼ĸè¾ij
    -0.09
    çĵ¶é¢Ī
    -0.09
    ادات
    -0.09
    POSITIVE LOGITS
    åĿ¡
    0.18
     slope
    0.14
    å±±åĿ¡
    0.12
    éĻ¡
    0.12
    æĸľ
    0.12
     slopes
    0.11
    slope
    0.11
    _slope
    0.11
     steep
    0.11
    1
    0.10
    Activations Density 0.040%

    No Known Activations