© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    error messages and contexts

    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
    olly
    -0.09
    åĬŁå¤«
    -0.09
    åŃIJéĩĮ
    -0.09
    ned
    -0.09
    soever
    -0.09
    yard
    -0.09
    娥
    -0.08
    nx
    -0.08
    /her
    -0.08
    nak
    -0.08
    POSITIVE LOGITS
    ormsg
    0.12
    fully
    0.12
    Occurred
    0.12
    _OCCURRED
    0.11
    inne
    0.10
    Õ£
    0.10
    æĦ«
    0.09
    swith
    0.09
    .typ
    0.09
    /disable
    0.09
    Activations Density 0.107%

    No Known Activations