© 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. 23376
    Prev
    Next
    INDEX
    Explanations

    in 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
    ilter
    -0.10
    ç±»åĪ«
    -0.10
    _HW
    -0.10
    æ²®
    -0.09
    Jar
    -0.09
    åĺ´å·´
    -0.09
    Hur
    -0.09
    çĸ¾
    -0.09
    opies
    -0.09
    AllWindows
    -0.09
    POSITIVE LOGITS
     society
    0.10
    è¨Ĺ
    0.09
     Lent
    0.08
    ENT
    0.08
     pant
    0.08
    æĹ©æĻļ
    0.08
    atile
    0.08
    less
    0.08
     imm
    0.08
    Revision
    0.07
    Activations Density 0.100%

    No Known Activations