© 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. 29849
    Prev
    Next
    INDEX
    Explanations

    relationship, separated, eternal life

    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
    éĢĢ
    -0.11
    å±Ĥåĩº
    -0.10
    å¾ģéĽĨ
    -0.09
    ä¸ī次
    -0.09
    åĬ²
    -0.09
    强壮
    -0.08
    Spatial
    -0.08
    èĪª
    -0.08
    两次
    -0.08
    çŀĭ
    -0.08
    POSITIVE LOGITS
    åħ³ç³»
    0.10
     relationship
    0.10
    亲è¿ij
    0.10
    éĹľä¿Ĥ
    0.10
    亲æĥħ
    0.09
    åIJ®
    0.09
    æŁĦ
    0.09
     конÑĤак
    0.09
    æķŀ
    0.09
    åºļ
    0.09
    Activations Density 0.049%

    No Known Activations