© 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. 54039
    Prev
    Next
    INDEX
    Explanations

    call a place home

    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
    åħ¨æĹ¥åĪ¶
    -0.10
    åĵij
    -0.09
    æĻĴ
    -0.09
    缼åħ¸
    -0.09
     discipline
    -0.09
    产åĵģçłĶåıij
    -0.09
    车åŀĭ
    -0.09
    è¡Įèµ°
    -0.09
    æĻ¤
    -0.08
    gar
    -0.08
    POSITIVE LOGITS
     home
    0.18
    家åĽŃ
    0.18
    home
    0.16
    åĽŀ家
    0.14
     homes
    0.14
    HOME
    0.14
    .home
    0.13
    -home
    0.13
     HOME
    0.13
    ãĥĽãĥ¼ãĥł
    0.13
    Activations Density 0.072%

    No Known Activations