© 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. 11077
    Prev
    Next
    INDEX
    Explanations

    making new, confirmed by, forming

    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
    好è¯Ħ
    -0.10
    æĶĺ
    -0.09
    thood
    -0.09
    åĬ¡
    -0.09
    ä¸Ĭå²Ĺ
    -0.09
    _fixture
    -0.09
    å°Ŀ
    -0.08
     Sink
    -0.08
    ivan
    -0.08
    .Env
    -0.08
    POSITIVE LOGITS
    èĥĮ
    0.11
    ä¿¡åı·
    0.11
    åĬ¨èĥ½
    0.10
    éĺ»åĬĽ
    0.10
    _HT
    0.09
     Ñģигнал
    0.09
    ¾ç¤º
    0.09
    æĶ¶çĽĺ
    0.09
    æĮĩæķ°
    0.09
    æĮģèĤ¡
    0.09
    Activations Density 0.062%

    No Known Activations