© 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. 62260
    Prev
    Next
    INDEX
    Explanations

    steamer, ship, boat, theatre

    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
    mods
    -0.08
    åºij
    -0.08
    AGIC
    -0.08
     mote
    -0.08
    æ®ĸ
    -0.08
    åģļå·¥
    -0.08
    acid
    -0.08
    forest
    -0.08
    毫ä¸į
    -0.08
    ocard
    -0.08
    POSITIVE LOGITS
     Benton
    0.09
    æķĪçĽĬ
    0.09
    _HAL
    0.09
    æŶä¸į
    0.09
    ä¹ĭæĹħ
    0.09
    okit
    0.09
    éĺµéĺµ
    0.08
    ildo
    0.08
    起身
    0.08
    é£İä¿Ĺ
    0.08
    Activations Density 0.001%

    No Known Activations