© 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. 6414
    Prev
    Next
    INDEX
    Explanations

    early detection of diseases

    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
    edicine
    -0.10
    Ñģла
    -0.09
    èĩªçĦ¶èĢĮçĦ¶
    -0.09
    icont
    -0.09
    æĮ¤
    -0.09
    移
    -0.08
    blast
    -0.08
    _ld
    -0.08
    _https
    -0.08
    .selector
    -0.08
    POSITIVE LOGITS
    æĹ©æľŁ
    0.14
    åıijçİ°
    0.14
    æĹ©
    0.14
     early
    0.13
    åıijçİ°éĹ®é¢ĺ
    0.13
    æ¥Ķ
    0.13
    å°½æĹ©
    0.12
    early
    0.12
    åıĬæŶ
    0.12
     discovery
    0.11
    Activations Density 0.110%

    No Known Activations