© 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. 52945
    Prev
    Next
    INDEX
    Explanations

    stability and anchoring

    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
    обоÑĢ
    -0.09
    è·³èĪŀ
    -0.09
    æ½ľèĥ½
    -0.09
    éĤij
    -0.09
    æĭĵ宽
    -0.09
    çĪµ
    -0.09
    ä¼ļéĢłæĪIJ
    -0.09
    ç¬Ļ
    -0.08
    æĬ¬èµ·å¤´
    -0.08
    å¯ĨåĪĩ
    -0.08
    POSITIVE LOGITS
    稳å®ļ
    0.14
    éĶļ
    0.12
     anch
    0.12
    稳å®ļçļĦ
    0.12
    å®īå®ļ
    0.12
     stability
    0.12
     anchor
    0.11
    ç©©å®ļ
    0.11
     anchors
    0.11
     stead
    0.11
    Activations Density 0.037%

    No Known Activations