© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36158
    Prev
    Next
    INDEX
    Explanations

    tapping into new

    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
    owns
    -0.09
    	TokenName
    -0.09
    gift
    -0.09
    _TYPED
    -0.09
    ttl
    -0.09
     пÑĢим
    -0.08
    icios
    -0.08
    èµł
    -0.08
    astics
    -0.08
    ataka
    -0.08
    POSITIVE LOGITS
    æµģè¡Į
    0.09
    çĪĨåıij
    0.09
    sources
    0.09
    ç¦ģæŃ¢
    0.09
     sources
    0.09
     Wiring
    0.09
    ä¹ĭæĺŁ
    0.08
    奥æŀĹåĮ¹
    0.08
    æĢ»è§īå¾Ĺ
    0.08
    éªĪ
    0.08
    Activations Density 0.012%

    No Known Activations