© 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. 31311
    Prev
    Next
    INDEX
    Explanations

    fisheries and fishing industry

    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
    ennon
    -0.09
    æ²»çĹħ
    -0.09
     Bid
    -0.08
    è·¸
    -0.08
    ÅĽÄĩ
    -0.08
    å±Ģ
    -0.08
    éĢĢ
    -0.08
    ä»ķ
    -0.08
    éĢĢåĽŀ
    -0.08
    icy
    -0.08
    POSITIVE LOGITS
    eras
    0.09
    åĪ³
    0.09
    第ä¸Ģéĥ¨
    0.09
    roe
    0.09
    åĽ½äºº
    0.09
    LAY
    0.09
    åĽ½éĻħåIJĪä½ľ
    0.08
    åİŁæĸĻ
    0.08
    éłĤ
    0.08
    adder
    0.08
    Activations Density 0.035%

    No Known Activations