© 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. 35033
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åijĹ
    -0.10
     здоÑĢовÑĮÑı
    -0.09
    /logging
    -0.09
    说éģĵ
    -0.08
    åĬ«
    -0.08
    ç¬ijéģĵ
    -0.08
    纶
    -0.08
    adesh
    -0.08
    åIJ¾
    -0.08
     DisplayName
    -0.08
    POSITIVE LOGITS
    åĪĻ
    0.21
    éĤ£ä¹Ī
    0.20
     thì
    0.18
    åīĩ
    0.18
     then
    0.18
    ï¼ĮåĪĻ
    0.17
    éĤ£å°±
    0.17
    éĤ£éº¼
    0.17
     maka
    0.17
     alors
    0.16
    Activations Density 0.055%

    No Known Activations