© 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. 48801
    Prev
    Next
    INDEX
    Explanations

    land ownership and use

    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
    è¾ĩ
    -0.11
    land
    -0.10
    æĪIJè´¥
    -0.10
    åĽ½å®ī
    -0.10
    /lists
    -0.10
    éķ¿çĽ¸
    -0.09
    éĩľ
    -0.09
    .aspx
    -0.09
    è¿ĻéĩĮæľī
    -0.09
    ingly
    -0.09
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.12
    owners
    0.10
    wort
    0.09
    owner
    0.09
    åľ¨ä¸ŃåĽ½
    0.09
    ä¸Ĭæľī
    0.08
    åľ¨äº¬
    0.08
    rarian
    0.08
    åľ¨æĪijåĽ½
    0.08
    igu
    0.08
    Activations Density 0.015%

    No Known Activations