© 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. 30367
    Prev
    Next
    INDEX
    Explanations

    letters and alphabet

    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
    è²Ķ
    -0.10
    æ¦Ľ
    -0.09
    çĺ³
    -0.09
    åı£å¾Ħ
    -0.09
    BitFields
    -0.09
    ihil
    -0.09
    _CHAIN
    -0.09
    æļ´
    -0.09
    éŀŃ
    -0.09
    anford
    -0.08
    POSITIVE LOGITS
    åĢŁçĶ¨
    0.09
    åŃĹæ¯į
    0.09
    ark
    0.09
    æī¿
    0.09
     letters
    0.09
    Letter
    0.08
     letter
    0.08
    èĥ¡åŃIJ
    0.08
     Letter
    0.08
    letter
    0.08
    Activations Density 0.211%

    No Known Activations