© 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. 7475
    Prev
    Next
    INDEX
    Explanations

    biological processes and defects

    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
     ÑģобÑģÑĤвенно
    -0.10
    æĪĸå¤ļæĪĸå°ij
    -0.09
    æĤ»
    -0.09
    éļıå¤Ħ
    -0.09
    omatic
    -0.09
     tek
    -0.09
    aptic
    -0.09
    å¬ĸ
    -0.09
    StdString
    -0.09
    åĥŃ
    -0.09
    POSITIVE LOGITS
    ç½ķè§ģ
    0.09
    å°±åĥı
    0.08
    çķħéĢļ
    0.08
    æĸ°åĬł
    0.08
    åıĺ身
    0.08
    iron
    0.08
    æļ¢
    0.08
    æѤåīį
    0.07
    ä¸Ģä½ĵåĮĸ
    0.07
    çĿģ
    0.07
    Activations Density 0.518%

    No Known Activations