© 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. 62172
    Prev
    Next
    INDEX
    Explanations

    as if / as follows / as good as

    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
    æĸ¹åľĨ
    -0.11
    渺
    -0.11
    ifiers
    -0.10
    æ®Ĩ
    -0.09
    inator
    -0.09
    çľĭä¸Ĭåİ»
    -0.09
     Evo
    -0.09
    åŁĿ
    -0.09
    èĮ«
    -0.09
    èĤĥ
    -0.09
    POSITIVE LOGITS
    hone
    0.10
    ufe
    0.09
    unge
    0.08
    æĪı
    0.08
    nte
    0.08
    åĩºè®©
    0.08
    æĮŁ
    0.08
    ought
    0.07
    éĺ¶
    0.07
    å¬
    0.07
    Activations Density 0.010%

    No Known Activations