© 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. 56192
    Prev
    Next
    INDEX
    Explanations

    deer hunting

    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
    ãĥ¡ãĥ³ãĥĪ
    -0.09
    airo
    -0.09
    è¾ĺ
    -0.09
    Powered
    -0.09
     scor
    -0.09
    LB
    -0.09
     tắc
    -0.09
    ives
    -0.08
    éĻIJæľŁ
    -0.08
    两岸
    -0.08
    POSITIVE LOGITS
    ë³µ
    0.09
    spam
    0.09
    igel
    0.09
    roll
    0.09
    ress
    0.08
    iaux
    0.08
    -roll
    0.08
    æİī
    0.08
     prowess
    0.08
    igu
    0.08
    Activations Density 0.015%

    No Known Activations