© 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. 3808
    Prev
    Next
    INDEX
    Explanations

    independent organizations

    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
    æĮ¤
    -0.09
    hen
    -0.09
    ho
    -0.09
    orris
    -0.08
    (___
    -0.08
    æĥħ
    -0.08
    __$
    -0.08
    åıĤä¸İ
    -0.08
    unta
    -0.08
    æ³Ħ
    -0.08
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.21
    Independent
    0.19
    çį¨ç«ĭ
    0.19
     Independent
    0.17
     independent
    0.17
     Independ
    0.16
     independents
    0.14
    Independ
    0.13
     independently
    0.13
    -independent
    0.13
    Activations Density 0.072%

    No Known Activations