© 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. 21715
    Prev
    Next
    INDEX
    Explanations

    iHeartMedia or Media Group

    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
    ushman
    -0.10
    丼æŀĹ
    -0.09
    山谷
    -0.09
    论
    -0.09
    coon
    -0.09
    spe
    -0.08
    å¾ĹçĽĬ
    -0.08
    _ACTIVITY
    -0.08
    .RunWith
    -0.08
    å°ĨåĨĽ
    -0.08
    POSITIVE LOGITS
    åīį身
    0.10
    è¹Ī
    0.09
    缴å±ŀ
    0.08
    çĶ
    0.08
     ringing
    0.08
    esc
    0.08
     vac
    0.08
    ç¼ħ
    0.08
    ç¾İ好
    0.07
    åĿIJä¸ĭ
    0.07
    Activations Density 0.179%

    No Known Activations