© 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. 11165
    Prev
    Next
    INDEX
    Explanations

    Polish names and words

    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
    çĶ°
    -0.09
    adia
    -0.09
    ëĦĪ
    -0.09
    æĿ¥çĶµ
    -0.09
    æŁĬ
    -0.09
    olle
    -0.09
    èĽ±
    -0.09
    ells
    -0.08
    oller
    -0.08
    åı¯è§Ĩ
    -0.08
    POSITIVE LOGITS
    åł¡
    0.10
    è±ģ
    0.09
    çĪµ
    0.09
    ä»»ä½ķ
    0.09
    æĬµå¾¡
    0.08
    à¹ĥà¸Ī
    0.08
    nat
    0.08
    éĿ¢
    0.08
    æĽľ
    0.08
    çĵ´
    0.08
    Activations Density 0.092%

    No Known Activations