© 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. 33116
    Prev
    Next
    INDEX
    Explanations

    long duration or lifespan

    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
    ÑģÑĤÑĭ
    -0.10
    lazy
    -0.10
     Ans
    -0.08
    大çīĩ
    -0.08
    oss
    -0.08
    ola
    -0.08
    çł·
    -0.08
    è¯Ńæ°Ķ
    -0.08
    rew
    -0.08
    lse
    -0.08
    POSITIVE LOGITS
    寿åij½
    0.25
    使çĶ¨å¯¿åij½
    0.22
     longevity
    0.19
    éķ¿å¯¿
    0.18
    æĮģä¹ħ
    0.17
     lifespan
    0.17
    壽
    0.16
    èĢIJçĶ¨
    0.16
    ä¹ħ
    0.15
    å¹´éĻIJ
    0.14
    Activations Density 0.079%

    No Known Activations