© 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. 56022
    Prev
    Next
    INDEX
    Explanations

    animals performing actions

    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
    aina
    -0.09
     Prote
    -0.09
    æŀģ
    -0.09
    åıijè´§
    -0.09
    产ä¸ļæī¶è´«
    -0.08
    üb
    -0.08
    èĬĤ
    -0.08
    åIJĥäºı
    -0.08
    åĬŃ
    -0.08
    åħ³
    -0.08
    POSITIVE LOGITS
    梳
    0.13
    æĬļæij¸
    0.12
    å¼Ħ
    0.11
    idget
    0.11
    èĪIJ
    0.10
    æIJĶ
    0.10
    ç¾½æ¯Ľ
    0.10
    æīĭæĮĩ
    0.09
    æīĭä¸ŃçļĦ
    0.09
    orns
    0.09
    Activations Density 0.072%

    No Known Activations