© 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. 39584
    Prev
    Next
    INDEX
    Explanations

    concern and worry

    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
    apers
    -0.10
    uits
    -0.09
    alic
    -0.08
     ref
    -0.08
     princ
    -0.08
    ellers
    -0.08
    .Power
    -0.08
    é²ľ
    -0.08
    ivar
    -0.08
    æĺİçĻ½äºĨ
    -0.08
    POSITIVE LOGITS
    æĭħ忧
    0.24
     concern
    0.23
     concerns
    0.22
     preocup
    0.21
    æĭħå¿ĥ
    0.21
     Concern
    0.21
    åħ³åĪĩ
    0.20
    忧èĻij
    0.20
     worry
    0.19
     worries
    0.18
    Activations Density 0.081%

    No Known Activations