© 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. 53624
    Prev
    Next
    INDEX
    Explanations

    history and historians

    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
    裸
    -0.10
    æ¹Ľ
    -0.09
    çĶŁæ´»çݯå¢ĥ
    -0.09
    allon
    -0.09
    æīĵæĭĽåij¼
    -0.09
     Registr
    -0.08
    éĢıæ°Ķ
    -0.08
    æī£
    -0.08
    çµIJ
    -0.08
    å¾Ģè¿Ķ
    -0.08
    POSITIVE LOGITS
    åı²
    0.19
    åİĨåı²
    0.17
    åħļåı²
    0.17
     history
    0.16
    çļĦåİĨåı²
    0.16
    æŃ·åı²
    0.15
     historians
    0.15
    history
    0.15
     histories
    0.15
    (history
    0.15
    Activations Density 0.235%

    No Known Activations