© 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. 63705
    Prev
    Next
    INDEX
    Explanations

    ending or related to 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
    èĤ¥
    -0.10
    丰
    -0.09
    éĴĵ
    -0.09
    -local
    -0.09
    以åħ¶
    -0.09
    omens
    -0.09
    çľĭä¸Ģä¸ĭ
    -0.09
    ORIA
    -0.09
    éĺģ
    -0.09
    zet
    -0.09
    POSITIVE LOGITS
    ç°Į
    0.09
    è¿Ļå¼ł
    0.08
    idl
    0.08
    din
    0.08
    è¿Ļä¹Īä¹ħ
    0.08
    udo
    0.08
    è¿Ļ个æĹ¶ä»£
    0.08
    pty
    0.08
     moderne
    0.08
    ä¹ħäºĨ
    0.08
    Activations Density 0.106%

    No Known Activations