© 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. 60653
    Prev
    Next
    INDEX
    Explanations

    crackers and chips

    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
    elman
    -0.10
    alf
    -0.10
    elor
    -0.09
    Calculator
    -0.09
    _lift
    -0.09
    anders
    -0.09
    gap
    -0.09
    .tk
    -0.08
     dank
    -0.08
    rog
    -0.08
    POSITIVE LOGITS
    board
    0.10
     crackers
    0.09
    éģĵçIJĨ
    0.09
    çĻ«çĹ«çĹħ
    0.08
    éĴµ
    0.08
    çĽĴåŃIJ
    0.07
    åĺ¶
    0.07
    设计çIJĨ念
    0.07
    åĪĽéĢłæĢ§
    0.07
    ç»ĻæĤ¨
    0.07
    Activations Density 0.005%

    No Known Activations