© 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. 21967
    Prev
    Next
    INDEX
    Explanations

    junior following words

    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
    éĿŀ常好çļĦ
    -0.09
     iP
    -0.08
    ä¸įä½ı
    -0.08
    afi
    -0.08
    客
    -0.08
    å°Ĭ严
    -0.08
    rax
    -0.08
    OrDefault
    -0.08
    ĻĤ
    -0.08
     Grü
    -0.08
    POSITIVE LOGITS
    -most
    0.11
    çīĪ
    0.09
    hood
    0.09
    YTE
    0.09
    kus
    0.09
    itas
    0.09
    çݲ
    0.09
    atures
    0.08
    龸çİĭ
    0.08
     sắc
    0.08
    Activations Density 0.016%

    No Known Activations