© 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. 52610
    Prev
    Next
    INDEX
    Explanations

    straight path or direction

    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
    æijŃ
    -0.10
    phis
    -0.10
    åĭŁéĽĨ
    -0.09
    oret
    -0.09
    åĪĨ红
    -0.09
    iage
    -0.09
    å¸Ľ
    -0.08
    hower
    -0.08
    æİ
    -0.08
    ä»ĵ
    -0.08
    POSITIVE LOGITS
     straight
    0.19
    straight
    0.17
     Straight
    0.16
    缴
    0.16
    çĽ´çº¿
    0.16
    Straight
    0.15
     thẳng
    0.12
    ä»ĭ
    0.11
    #line
    0.11
    æķ´é½IJ
    0.11
    Activations Density 0.043%

    No Known Activations