© 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. 53877
    Prev
    Next
    INDEX
    Explanations

    loose .dtd

    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
    FOX
    -0.09
    ä¸į幸
    -0.09
    讼
    -0.09
     punct
    -0.09
    Ñıвление
    -0.09
    éĤ»
    -0.09
    ä¸į容
    -0.09
    @",
    -0.09
    ersistence
    -0.08
    æ·±
    -0.08
    POSITIVE LOGITS
     loose
    0.19
     Loose
    0.17
    æĿ¾
    0.16
    é¬Ĩ
    0.15
     loosen
    0.13
     loosely
    0.12
     loos
    0.11
    é©°
    0.10
    èĩªåľ¨
    0.10
    æĩĪ
    0.09
    Activations Density 0.040%

    No Known Activations