© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52301
    Prev
    Next
    INDEX
    Explanations

    successful outcomes

    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
    ang
    -0.10
    bound
    -0.09
    å°ıåŃ©
    -0.09
    resse
    -0.09
    felt
    -0.09
    æķķ
    -0.09
    bane
    -0.08
    èĢģèĻİ
    -0.08
    ijd
    -0.08
    enced
    -0.08
    POSITIVE LOGITS
    ness
    0.14
    ive
    0.12
    -looking
    0.12
    ivity
    0.12
    OperationException
    0.11
    lest
    0.11
    arian
    0.09
    ly
    0.09
    -minded
    0.09
     ÙĦÙĦغاÙĬØ©
    0.09
    Activations Density 0.019%

    No Known Activations