© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22338
    Prev
    Next
    INDEX
    Explanations

    narrow down to

    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
    tober
    -0.10
    поÑĢ
    -0.09
    oney
    -0.09
    okia
    -0.09
    .DataType
    -0.09
    æĥ¬
    -0.09
    éĩijèī²
    -0.09
    _ENTER
    -0.09
    oti
    -0.09
    ramids
    -0.09
    POSITIVE LOGITS
    éĻįåĪ°
    0.20
    éĻįèĩ³
    0.19
    å¢ŀèĩ³
    0.18
    åıĺæĪIJäºĨ
    0.15
    åıĺæĪIJ
    0.14
    åĪ°äºĨ
    0.13
    åĪ°
    0.13
    åıĺ为
    0.13
    æĪIJéķ¿ä¸º
    0.13
    ToOne
    0.10
    Activations Density 0.109%

    No Known Activations