© 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. 4049
    Prev
    Next
    INDEX
    Explanations

    everywhere, ubiquitous

    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
     Ñĥдал
    -0.09
    éĶ¶
    -0.08
    prog
    -0.08
    zone
    -0.08
    WO
    -0.08
    åĪĹåĩº
    -0.08
    baum
    -0.08
    访è°Ī
    -0.08
    åħ·ä½ĵåĨħ容
    -0.08
    æŃ£å¥½
    -0.08
    POSITIVE LOGITS
     everywhere
    0.24
    éļıå¤Ħåı¯è§ģ
    0.21
    åĪ°å¤Ħ
    0.20
    éļıå¤Ħ
    0.19
     Everywhere
    0.19
    å¤Ħå¤Ħ
    0.18
    åĽĽå¤Ħ
    0.16
     khắp
    0.15
    éģįåıĬ
    0.14
    éģįå¸ĥ
    0.14
    Activations Density 0.132%

    No Known Activations