© 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. 58954
    Prev
    Next
    INDEX
    Explanations

    band around

    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
    ég
    -0.09
    伸æīĭ
    -0.09
    ssf
    -0.08
    éĩĩçĶ¨äºĨ
    -0.08
    bo
    -0.08
    èIJ½åľ°
    -0.08
    eof
    -0.08
    Ñħи
    -0.08
    éĿ¢å®¹
    -0.08
    ancing
    -0.08
    POSITIVE LOGITS
     Bands
    0.12
    ç¼ł
    0.11
     bands
    0.11
    åĮħ裹
    0.11
    Band
    0.10
    èĽĩ
    0.10
     banda
    0.10
    æįĤ
    0.10
    çĥĻ
    0.10
    ä¸įä¸ĭ
    0.10
    Activations Density 0.129%

    No Known Activations