© 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. 27577
    Prev
    Next
    INDEX
    Explanations

    largest

    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
    nic
    -0.09
    å°ij许
    -0.09
    åĩłæ¬¡
    -0.09
    æįħ
    -0.08
    çģ¿çĥĤ
    -0.08
    éĹ°
    -0.08
    侮辱
    -0.08
    ultimate
    -0.08
    äºĨä¸Ģéģį
    -0.08
    iant
    -0.08
    POSITIVE LOGITS
    è§Ħ模
    0.11
    ä¸Ķ
    0.10
    -largest
    0.10
    ä½ĵéĩı
    0.10
     ever
    0.09
    æĹłç¼Ŀ
    0.09
    -ever
    0.09
    size
    0.09
    èIJ½åľ°
    0.09
    æĪIJè´¥
    0.09
    Activations Density 0.078%

    No Known Activations