© 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. 51217
    Prev
    Next
    INDEX
    Explanations

    explain, identify, pinpoint

    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
    èĮĨ
    -0.10
    anova
    -0.09
     мн
    -0.09
    ROLS
    -0.09
    anzeigen
    -0.09
     Beit
    -0.08
    缸åħ³åĨħ容
    -0.08
    åģļ强
    -0.08
    åIJ¬çĿĢ
    -0.08
    íĥij
    -0.08
    POSITIVE LOGITS
    说ä¸įåĩº
    0.12
    说åĩº
    0.11
    说åĩºæĿ¥
    0.11
    ç¡®åĪĩ
    0.10
     ÑĤоÑĩно
    0.10
    åİŁåĽł
    0.09
    3
    0.09
     exactly
    0.09
    表述
    0.09
    åħ·ä½ĵ
    0.09
    Activations Density 0.105%

    No Known Activations