© 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. 34424
    Prev
    Next
    INDEX
    Explanations

    playground and outdoor activities

    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
     lodging
    -0.10
    å¾Ģå¤ĸ
    -0.10
    槽
    -0.09
    轸
    -0.09
    æĬ¬èµ·
    -0.09
    ç³Ł
    -0.09
     bunk
    -0.09
     подпиÑģ
    -0.08
    æĪIJåĵģ
    -0.08
    çĿ¡è§ī
    -0.08
    POSITIVE LOGITS
    å¥Ķè·ij
    0.13
    çİ©èĢį
    0.13
     playground
    0.11
    åħ¬åĽŃ
    0.11
    èįīåĿª
    0.10
     Playground
    0.10
    çİ©åħ·
    0.10
    çİ©
    0.10
    èĩªè¡Į车
    0.10
    èįīåľ°
    0.10
    Activations Density 0.050%

    No Known Activations