© 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. 10407
    Prev
    Next
    INDEX
    Explanations

    posting to other members

    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
    çĬģ
    -0.10
    声èªī
    -0.10
    ள
    -0.09
    legen
    -0.09
    æű
    -0.09
    赤
    -0.09
    æijĩ
    -0.08
    lege
    -0.08
    æĹłä¸į
    -0.08
    رÙħ
    -0.08
    POSITIVE LOGITS
    orns
    0.09
    imas
    0.09
    天ä¸ĭ
    0.08
    rien
    0.08
    zin
    0.08
    æĮģå¹³
    0.08
    ordes
    0.08
    -ST
    0.08
    çĩİ
    0.08
    abela
    0.08
    Activations Density 0.104%

    No Known Activations