© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52540
    Prev
    Next
    INDEX
    Explanations

    amazed, amazing, astounds, marvel

    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
    ä¹ĭ家
    -0.09
    åģĩ
    -0.09
     Vik
    -0.09
    bos
    -0.08
    leck
    -0.08
    ated
    -0.08
    íĬ¹ë³Ħ
    -0.08
    åĹħ
    -0.08
    å°´å°¬
    -0.08
    èī°éļ¾
    -0.08
    POSITIVE LOGITS
    ingly
    0.16
    ä¸įå·²
    0.11
    å¥ĩ迹
    0.10
    ç¥ŀéĢļ
    0.10
    ä¸į解
    0.09
    mir
    0.09
     feats
    0.09
    ably
    0.09
    _ATTRIB
    0.09
    常çĶ¨
    0.09
    Activations Density 0.009%

    No Known Activations