© 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. 31338
    Prev
    Next
    INDEX
    Explanations

    communication notes and messages

    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
    çĹĽ
    -0.11
    lys
    -0.09
    éºĴéºŁ
    -0.09
     Parr
    -0.08
    çģŃ
    -0.08
    è¿Ļä¹Īåģļ
    -0.08
    otime
    -0.08
    rias
    -0.08
    pdb
    -0.08
     Medi
    -0.08
    POSITIVE LOGITS
     messages
    0.15
     message
    0.13
    çķĻè¨Ģ
    0.12
    çŁŃä¿¡
    0.12
    messages
    0.12
    ãĥ¡ãĥĥãĤ»ãĥ¼ãĤ¸
    0.12
     Messages
    0.11
    .messages
    0.11
    è¾¾
    0.11
    æ¶Īæģ¯
    0.11
    Activations Density 0.080%

    No Known Activations