© 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. 33911
    Prev
    Next
    INDEX
    Explanations

    new territory or domain

    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
    åIJ¦
    -0.10
     ì²ĺ
    -0.10
    /lg
    -0.09
    ìķ¤
    -0.09
    åĮĹ约
    -0.09
    æĸĹ
    -0.09
    ä¸ĢæĶ¯
    -0.09
    è´«ç©·
    -0.09
     ба
    -0.09
    壽
    -0.09
    POSITIVE LOGITS
     territory
    0.15
     terrain
    0.13
    charted
    0.12
     Territory
    0.12
    éĻĮçĶŁ
    0.12
     unfamiliar
    0.11
     territories
    0.10
     terra
    0.10
     облаÑģÑĤÑĮ
    0.10
    å¹³åĿ¦
    0.09
    Activations Density 0.069%

    No Known Activations