© 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. 61318
    Prev
    Next
    INDEX
    Explanations

    fishing and related 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
     Phoenix
    -0.09
    lash
    -0.09
    èįīåİŁ
    -0.09
    æŀ«
    -0.08
    èľľèľĤ
    -0.08
    ailable
    -0.08
    æĸ¯é¡¿
    -0.08
    髦
    -0.08
    èĬŃ
    -0.08
    æĬ¥åĪĬ
    -0.08
    POSITIVE LOGITS
    éĴĵ
    0.20
    éĴĵé±¼
    0.18
     fishing
    0.17
    æ¸Ķ
    0.17
     Fishing
    0.16
    æ¸ĶèĪ¹
    0.16
    æįķé±¼
    0.15
     fish
    0.15
    æ¸Ķä¸ļ
    0.15
     fishes
    0.14
    Activations Density 0.130%

    No Known Activations