© 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. 10411
    Prev
    Next
    INDEX
    Explanations

    time spent with

    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¸ĢåĪĩéĥ½
    -0.10
    ä¸ĢåĪĩ
    -0.10
    MAC
    -0.09
    ktor
    -0.09
    çĩļ
    -0.09
    ä»İ严
    -0.09
    esse
    -0.08
    åħ³éĶ®æĬĢæľ¯
    -0.08
    imas
    -0.08
     Castillo
    -0.08
    POSITIVE LOGITS
    ä¸įå±ij
    0.08
     Meh
    0.08
     Châu
    0.08
     either
    0.08
    榻
    0.08
     tangent
    0.08
     actually
    0.08
    对çħ§æ£ĢæŁ¥
    0.08
    åIJĦæł·
    0.08
    å¹²çĩ¥
    0.08
    Activations Density 0.045%

    No Known Activations