© 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. 30773
    Prev
    Next
    INDEX
    Explanations

    geographical distribution and range

    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
    ä¸įèµ·
    -0.09
    åįĶ
    -0.09
    ARAM
    -0.09
    æĬĺ
    -0.09
    unda
    -0.08
    ä¸ī峡
    -0.08
     pwd
    -0.08
    phem
    -0.08
    teil
    -0.08
     Michelle
    -0.08
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.17
    å¹¿æ³ĽçļĦ
    0.13
    éģįåıĬ
    0.13
    éģįå¸ĥ
    0.12
    å¹¿æ³Ľ
    0.12
     distribution
    0.11
     DISTRIBUT
    0.11
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    0.11
    å¤ļåľ°
    0.10
    åĪĨå¸ĥåľ¨
    0.10
    Activations Density 0.194%

    No Known Activations