© 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. 56432
    Prev
    Next
    INDEX
    Explanations

    rules and permissions

    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
    ANGO
    -0.10
    opia
    -0.09
    æĶ¯æŁ±
    -0.09
    emic
    -0.09
    ugal
    -0.09
    uran
    -0.09
    .RegisterType
    -0.08
    èĥ¼
    -0.08
    .Cmd
    -0.08
    -space
    -0.08
    POSITIVE LOGITS
    è§ĦåĪĻ
    0.13
     rules
    0.12
    è§Ħ磩
    0.10
     flex
    0.10
    _rules
    0.10
    èĥ¡åŃIJ
    0.10
    æĿĪ
    0.10
     policies
    0.10
    æĿĥ
    0.10
     policy
    0.09
    Activations Density 0.169%

    No Known Activations