© 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. 4053
    Prev
    Next
    INDEX
    Explanations

    loved ones, family, and relationships

    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
    /terms
    -0.10
    @a
    -0.09
    æĿĥ
    -0.09
     minib
    -0.09
    æľīåĪ©
    -0.09
    çļĩå¸Ŀ
    -0.09
    ric
    -0.09
    çŃĭ
    -0.09
    大èĩ£
    -0.09
    ä¸įåĩºæĿ¥
    -0.08
    POSITIVE LOGITS
    亲人
    0.20
    家人
    0.19
     loved
    0.15
    亲åıĭ
    0.13
     Loved
    0.13
    亲å±ŀ
    0.12
    亲æĥħ
    0.11
    çĪ±ä½ł
    0.11
    亲çĪ±
    0.11
    身边
    0.10
    Activations Density 0.085%

    No Known Activations