© 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. 7175
    Prev
    Next
    INDEX
    Explanations

    heir, successor, inheritance, carry on

    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
    insn
    -0.09
    å¦Ĥä½ķçľĭå¾ħ
    -0.08
    æ´ĭèij±
    -0.08
    atar
    -0.08
    ä¸įéĢļ
    -0.08
    prob
    -0.08
    åħ¥æĪ·
    -0.08
    poses
    -0.08
    aho
    -0.08
    atican
    -0.08
    POSITIVE LOGITS
    继æī¿
    0.19
    ä¼łæī¿
    0.18
    éģĹ产
    0.16
     legacy
    0.15
    æİ¥åĬĽ
    0.14
     inheritance
    0.13
    延ç»Ń
    0.13
    æī¿
    0.13
     inherit
    0.13
    inherit
    0.12
    Activations Density 0.066%

    No Known Activations