© 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. 61395
    Prev
    Next
    INDEX
    Explanations

    magnetic properties

    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
    æľ¬åľŁ
    -0.10
     Alto
    -0.09
    orn
    -0.09
     полноÑģÑĤÑĮÑİ
    -0.09
    omin
    -0.09
    åĪĩåħ¥
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    å¤ĸåĽ´
    -0.09
    çķ¥
    -0.08
    é©¿
    -0.08
    POSITIVE LOGITS
    ç£ģ
    0.13
     magnetic
    0.11
    ç£ģåľº
    0.11
    éĴĵ
    0.11
     magnets
    0.10
    éĢĬ
    0.10
    åĮĹæŀģ
    0.10
    agnetic
    0.09
    agher
    0.09
    æĭīå¼Ģ
    0.09
    Activations Density 0.101%

    No Known Activations