© 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. 22994
    Prev
    Next
    INDEX
    Explanations

    subject to change

    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
    åĨ¤
    -0.10
    нев
    -0.10
     Chall
    -0.09
    ervas
    -0.09
    éķ²
    -0.09
    èģĶç³»
    -0.08
    1
    -0.08
    5
    -0.08
    4
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.12
    åħ·ä½ĵæĥħåĨµ
    0.11
    éģµå®Ī
    0.10
    æĤ¨åIJĮæĦı
    0.10
    å½ĵæŶçļĦ
    0.10
    å®ŀéĻħæĥħåĨµ
    0.09
    大çĽĺ
    0.09
    çķ¶æĻĤ
    0.09
    atif
    0.09
    batim
    0.09
    Activations Density 0.009%

    No Known Activations