© 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. 5255
    Prev
    Next
    INDEX
    Explanations

    template and theme components

    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
    ührung
    -0.09
     diamond
    -0.08
    ÙĦÙĪÙħ
    -0.08
    peg
    -0.08
     Ole
    -0.08
    aber
    -0.08
    6
    -0.07
    ADOR
    -0.07
    uler
    -0.07
    Diamond
    -0.07
    POSITIVE LOGITS
    åı¯ä¾Ľ
    0.11
    æ»´
    0.11
    åºĵéĩĮ
    0.10
    åı¯çĶ¨
    0.10
    sgi
    0.10
    åºĵ
    0.09
    大åħ¨
    0.09
    INGTON
    0.09
    ç¢İçīĩ
    0.09
    æĬĬä½ł
    0.09
    Activations Density 0.040%

    No Known Activations