© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    once again

    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
    éĶIJ
    -0.10
    ield
    -0.10
    loon
    -0.10
    æªĢ
    -0.10
    zzle
    -0.09
    çĭłæĬĵ
    -0.09
    ลà¸ļ
    -0.09
    hammer
    -0.09
     mos
    -0.09
    å¾Īå°ij
    -0.09
    POSITIVE LOGITS
     again
    0.13
    again
    0.12
    åIJĮæł·æĺ¯
    0.12
    åĨįä¸Ģ次
    0.11
    åĨį次
    0.11
    åıĪä¸Ģ次
    0.11
     Again
    0.10
    å¤§åľ°
    0.10
    AGAIN
    0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.09
    Activations Density 0.010%

    No Known Activations