© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6796
    Prev
    Next
    INDEX
    Explanations

    stance, attitude, view, approach, policy

    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
    ugin
    -0.09
    å¾Ĺä¸įåĪ°
    -0.09
    onder
    -0.09
    çĶŁåij½åĬĽ
    -0.09
    itary
    -0.09
    ÙĦÙĪ
    -0.09
    æķ´é¡¿
    -0.09
    gression
    -0.09
    çĪĨæĸĻ
    -0.09
    ikki
    -0.09
    POSITIVE LOGITS
     approach
    0.13
    çļĦæĢģ度
    0.13
     attitude
    0.12
    æĢģ度
    0.12
    è§ĤæľĽ
    0.10
     Approach
    0.10
    appro
    0.10
    çŃĸçķ¥
    0.10
    éĢ¢
    0.10
    对å¾ħ
    0.10
    Activations Density 0.050%

    No Known Activations