© 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. 24018
    Prev
    Next
    INDEX
    Explanations

    waterproof, hydrophobic, resistance

    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
    CAPE
    -0.10
    ifice
    -0.09
    SAN
    -0.08
     nhá»±a
    -0.08
    iously
    -0.08
    踯
    -0.08
    ç»İ
    -0.08
     Nass
    -0.08
    ãģ¨ãģĹãģ¦
    -0.08
    éĺ³åİ¿
    -0.08
    POSITIVE LOGITS
    ä¸Ŀ毫
    0.10
    è§ī
    0.09
    åĸľ
    0.09
    å°ī
    0.08
    缴è§Ĥ
    0.08
    xda
    0.08
    ä»»
    0.08
     Disneyland
    0.08
    Doctrine
    0.08
    gent
    0.08
    Activations Density 0.004%

    No Known Activations