© 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. 54663
    Prev
    Next
    INDEX
    Explanations

    cold water, war, blood, turkey, plasma

    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
    ively
    -0.10
    ãĥ¡ãĥ³ãĥĪ
    -0.09
    naire
    -0.09
    稷
    -0.09
    chan
    -0.09
    éĻIJãĤĬ
    -0.09
     Pett
    -0.09
    cation
    -0.09
    illis
    -0.09
    erial
    -0.08
    POSITIVE LOGITS
    ness
    0.14
    -hearted
    0.13
    -blood
    0.13
    smith
    0.12
     lẽ
    0.11
    æ³»
    0.11
    NESS
    0.10
    tant
    0.10
    foot
    0.10
    /free
    0.10
    Activations Density 0.016%

    No Known Activations