© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8798
    Prev
    Next
    INDEX
    Explanations

    secure, verified, free, excellence

    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
     subscriptions
    -0.09
    æ¿ij
    -0.09
     embar
    -0.09
    åĭŁ
    -0.08
     subscription
    -0.08
    èµĦåĬ©
    -0.08
    çĸıéĢļ
    -0.08
    iri
    -0.08
    oid
    -0.08
    æł·åŃIJ
    -0.07
    POSITIVE LOGITS
     TripAdvisor
    0.10
    为æĤ¨æıIJä¾Ľ
    0.10
    æIJºç¨ĭ
    0.09
    度åģĩ
    0.09
    _booking
    0.09
     ÑĤÑĥÑĢиÑģÑĤ
    0.09
    客人
    0.09
     Guests
    0.09
    æĹħ客
    0.09
     оÑĤз
    0.09
    Activations Density 0.108%

    No Known Activations