© 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. 17937
    Prev
    Next
    INDEX
    Explanations

    Martin followed by a surname

    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
    ingly
    -0.17
    ãģ£ãģįãĤĬ
    -0.11
    çĶŁæŃ»
    -0.11
    edList
    -0.10
    pper
    -0.10
    sic
    -0.10
    ivity
    -0.10
    sWith
    -0.09
    æģģ
    -0.09
    éģ½
    -0.09
    POSITIVE LOGITS
    elli
    0.13
    sson
    0.09
    son
    0.09
     Luther
    0.09
    ique
    0.09
    ello
    0.09
    ussen
    0.09
    åī¯å¸Ĥéķ¿
    0.08
    ady
    0.08
    istry
    0.08
    Activations Density 0.019%

    No Known Activations