© 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. 37761
    Prev
    Next
    INDEX
    Explanations

    look at

    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
    ilm
    -0.08
    ilton
    -0.08
    kit
    -0.08
    æħ¢æħ¢åľ°
    -0.08
    forth
    -0.08
    ä¸ĢçĤ¹çĤ¹
    -0.08
    oodle
    -0.08
     наÑĪиÑħ
    -0.08
    ilt
    -0.08
    æĮĩå°ĸ
    -0.08
    POSITIVE LOGITS
    AndFeel
    0.15
    ipy
    0.12
    ä¸Ģçľ¼
    0.11
    ä¸Ģçľĭ
    0.10
    UpEdit
    0.10
    еÑĤÑĮ
    0.10
    ettel
    0.10
    áŀĦ
    0.10
    éķ¿è¿ľ
    0.10
    elihood
    0.09
    Activations Density 0.054%

    No Known Activations