© 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. 3521
    Prev
    Next
    INDEX
    Explanations

    make something happen

    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
    æŃ£æĸĩ
    -0.11
    usk
    -0.10
    ingo
    -0.10
    rd
    -0.09
    æ¡£
    -0.09
    osen
    -0.09
    ogens
    -0.09
    åıĹéĤĢ
    -0.09
    á»ĩp
    -0.09
    imity
    -0.08
    POSITIVE LOGITS
    æľīæīĢ
    0.10
     sure
    0.09
    åıijçĶŁçļĦ
    0.08
    éĿłè¿ij
    0.08
    åĬ¨
    0.08
     tap
    0.08
    äºĪ以
    0.08
    èĬ®
    0.08
    çİ°æľī
    0.07
    çĶ¨åĬĽ
    0.07
    Activations Density 0.060%

    No Known Activations