© 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. 38385
    Prev
    Next
    INDEX
    Explanations

    key, keys, signature, token

    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
    éĺ²çĽĹ
    -0.09
    6
    -0.08
    9
    -0.08
    0
    -0.08
    7
    -0.08
    erre
    -0.08
    8
    -0.08
    dra
    -0.08
    å¾ĭ
    -0.08
    1
    -0.08
    POSITIVE LOGITS
    éķ¿éĢĶ
    0.10
    assel
    0.10
    檢
    0.10
    æ£Ģ
    0.09
    alli
    0.09
     ìĦľ
    0.09
     endwhile
    0.09
    é«ĺæĺĤ
    0.08
    .Inner
    0.08
     Plains
    0.08
    Activations Density 0.148%

    No Known Activations