© 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. 19245
    Prev
    Next
    INDEX
    Explanations

    differential signal

    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
    èĢ¶ç¨£
    -0.09
    西路
    -0.09
    èIJ
    -0.09
    è··
    -0.08
    åijĺ
    -0.08
    梧
    -0.08
    çĮľ
    -0.08
    æŁ¿
    -0.08
    æĤ²
    -0.08
    OLS
    -0.08
    POSITIVE LOGITS
    ä¸Ģä½ĵåĮĸ
    0.09
     cred
    0.08
    IMP
    0.08
    ừng
    0.08
    èĩªæľī
    0.08
     closet
    0.08
    liable
    0.08
    ä¹Łä¸į
    0.08
    ning
    0.08
    .qq
    0.08
    Activations Density 1.335%

    No Known Activations