© 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. 6821
    Prev
    Next
    INDEX
    Explanations

    locations or dates

    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
    æĭ¨
    -0.09
    eus
    -0.08
    hir
    -0.08
    itsu
    -0.08
    izard
    -0.08
    è´«ç©·
    -0.08
    çĭ°
    -0.08
    æĹ©çĤ¹
    -0.07
    ocl
    -0.07
     Resident
    -0.07
    POSITIVE LOGITS
    æħ¨
    0.11
     HÃłng
    0.10
    èµ°è¿ij
    0.09
     cặp
    0.09
    æĸ°éĹ»åıijå¸ĥ
    0.09
    ç¬ij声
    0.09
    æĤĴ
    0.09
    对çĿĢ
    0.09
     compan
    0.08
    è·¯è¿ĩ
    0.08
    Activations Density 0.107%

    No Known Activations