© 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. 29991
    Prev
    Next
    INDEX
    Explanations

    durability and longevity

    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
    æĶ¶æĶ¯
    -0.12
    æĹ¥å¤ľ
    -0.09
    åĨ²
    -0.09
    æIJ¬åĪ°
    -0.09
    åĩºåħ¥
    -0.09
    干货
    -0.09
    å®īç½®
    -0.09
    ä½ľæģ¯
    -0.08
    ervation
    -0.08
    /licenses
    -0.08
    POSITIVE LOGITS
    èĢIJçĶ¨
    0.18
     durability
    0.15
    ç»Ī身
    0.13
    使çĶ¨å¯¿åij½
    0.13
     durable
    0.12
    åĶ®åIJİ
    0.12
     lifetime
    0.12
    dur
    0.12
    Dur
    0.11
    æĮģä¹ħ
    0.11
    Activations Density 0.204%

    No Known Activations