© 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. 63714
    Prev
    Next
    INDEX
    Explanations

    heading or headed to

    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
    plier
    -0.09
    _skb
    -0.08
    edata
    -0.08
    鸢
    -0.08
    éļıå¤Ħ
    -0.08
    ей
    -0.08
    æĪijæīį
    -0.08
    blr
    -0.08
    avity
    -0.08
    PH
    -0.08
    POSITIVE LOGITS
    itor
    0.10
     Ñģем
    0.09
    æ¸Ń
    0.09
    /she
    0.09
    ¨
    0.09
    forth
    0.09
    .ind
    0.09
    usband
    0.08
    ÑĢед
    0.08
    prises
    0.08
    Activations Density 0.008%

    No Known Activations