© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59207
    Prev
    Next
    INDEX
    Explanations

    Hope then concluding phrases

    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
    Negative Logits
    åºĶ该å¦Ĥä½ķ
    -0.11
    6
    -0.10
    åĪ°åºķæĺ¯
    -0.09
    å²Ĥ
    -0.09
    rees
    -0.09
    åĶĩ
    -0.09
    èĻ½è¯´
    -0.09
    åºĶ该æĢİä¹Ī
    -0.09
    4
    -0.09
    8
    -0.09
    POSITIVE LOGITS
    ajas
    0.10
     Marty
    0.10
    writers
    0.09
    ULER
    0.09
    inality
    0.09
    lessly
    0.09
    olis
    0.09
    è½½
    0.08
    ient
    0.08
    maid
    0.08
    Activations Density 0.019%

    No Known Activations