© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9237
    Prev
    Next
    INDEX
    Explanations

    state v

    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
    便
    -0.10
    pret
    -0.10
    inking
    -0.10
    è¶³
    -0.09
    çݰæľī
    -0.09
    çł·
    -0.09
    BEST
    -0.09
    çIJĨçͱ
    -0.08
    èĦ±
    -0.08
    ä¸įçͱå¾Ĺ
    -0.08
    POSITIVE LOGITS
    iets
    0.09
    @m
    0.08
    atters
    0.08
    绪
    0.08
    èķĪ
    0.08
    èIJ½
    0.08
    ervations
    0.08
    仨
    0.08
    èij©
    0.07
    atter
    0.07
    Activations Density 0.219%

    No Known Activations