© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51087
    Prev
    Next
    INDEX
    Explanations

    select the

    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
    çĽĤ
    -0.12
    ForResult
    -0.10
    欣åĸľ
    -0.09
    год
    -0.08
     IMG
    -0.08
    _extraction
    -0.08
    é£ŀè·ĥ
    -0.08
    _SHARED
    -0.08
    ç¼ĥ
    -0.08
    ä¼Ĭå§ĭ
    -0.08
    POSITIVE LOGITS
    æĪij认为
    0.11
    认为
    0.10
    èªįçĤº
    0.10
    ä»ĸ认为
    0.10
    (s
    0.09
    æĪij们认为
    0.09
    æıŃéľ²
    0.09
    canonical
    0.09
    uck
    0.09
    太å°ij
    0.09
    Activations Density 0.048%

    No Known Activations