© 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. 20121
    Prev
    Next
    INDEX
    Explanations

    let you

    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
    å¤©åľ°
    -0.09
     Lik
    -0.09
    å¤ĩ
    -0.09
    å§Ĺ
    -0.08
     Jal
    -0.08
    semble
    -0.08
    lik
    -0.08
     withheld
    -0.08
    likelihood
    -0.08
    _mgr
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.16
     anymore
    0.12
    ä»»ä½ķ人
    0.12
    ä»»ä½ķ
    0.11
    æĪIJ为ä¸Ģ个
    0.11
    æĪIJ为
    0.10
    å°±è¿Ļä¹Ī
    0.10
    ä»»ä½ķä¸Ģ个
    0.10
    æĤ²è§Ĥ
    0.10
    ipt
    0.09
    Activations Density 0.032%

    No Known Activations