© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11707
    Prev
    Next
    INDEX
    Explanations

    harvesting season and activities

    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
    ities
    -0.10
    çģ¶
    -0.10
    alties
    -0.09
    verted
    -0.09
    ified
    -0.09
    atically
    -0.09
    chip
    -0.08
    leness
    -0.08
    æŃ»åIJİ
    -0.08
    커
    -0.08
    POSITIVE LOGITS
    æ®Ĩ
    0.11
    æŃī
    0.10
    à¸ķà¸ģ
    0.09
     дог
    0.09
     полÑĮзÑĥ
    0.09
    ÙĦاÙĨ
    0.09
    管çIJĨåijĺ
    0.09
    åĬĽéĩı
    0.09
    tings
    0.09
    äºĨ许å¤ļ
    0.09
    Activations Density 0.010%

    No Known Activations