© 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. 33971
    Prev
    Next
    INDEX
    Explanations

    apartment / flat / housing

    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
    оÑģÑĮ
    -0.11
    atra
    -0.10
    æĿĸ
    -0.10
    æ¯Ķäºļ
    -0.09
    arning
    -0.09
    fully
    -0.09
    -0.09
    heck
    -0.09
    вин
    -0.09
    -INF
    -0.09
    POSITIVE LOGITS
    tern
    0.10
    iable
    0.10
    iates
    0.10
    -scale
    0.09
    MENT
    0.09
    arium
    0.08
    Ñĩин
    0.08
    cel
    0.08
    hone
    0.08
    -sized
    0.08
    Activations Density 0.009%

    No Known Activations