© 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. 53211
    Prev
    Next
    INDEX
    Explanations

    intensifiers followed by adjectives

    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
    IME
    -0.11
    ç¨ļ
    -0.10
    gression
    -0.10
     trÃŃ
    -0.10
    空åīį
    -0.10
    velope
    -0.09
    æĤĮ
    -0.09
    airo
    -0.09
    NIC
    -0.09
    imson
    -0.09
    POSITIVE LOGITS
     "
    0.08
    ç½ij讯
    0.08
    æ´µ
    0.08
    apat
    0.08
    åį±å®³
    0.08
    æĻļæľŁ
    0.08
    çļĦé£İéĻ©
    0.07
     Dal
    0.07
    çĶ¸
    0.07
    OUS
    0.07
    Activations Density 0.006%

    No Known Activations