© 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. 52748
    Prev
    Next
    INDEX
    Explanations

    virus and 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
    roud
    -0.10
    ©
    -0.09
    æľĪä¸ĭ
    -0.09
    eenth
    -0.09
    Ñī
    -0.09
    èĻ±
    -0.09
     Reese
    -0.08
    rench
    -0.08
    resse
    -0.08
    ¹
    -0.08
    POSITIVE LOGITS
    uide
    0.10
    ically
    0.10
    çĸ£
    0.09
    械
    0.08
    åĶij
    0.08
    大éĺŁ
    0.08
    çľŃ
    0.08
    like
    0.08
    aceous
    0.08
    زا
    0.08
    Activations Density 0.045%

    No Known Activations