© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14239
    Prev
    Next
    INDEX
    Explanations

    illegal activities, drugs, and persons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    iller
    -0.20
    大å±Ģ
    -0.18
    ç¿©
    -0.17
    çĪ¸
    -0.16
    ween
    -0.15
    blr
    -0.15
    åľľ
    -0.15
    /body
    -0.15
    oref
    -0.15
     vÃŃt
    -0.15
    POSITIVE LOGITS
    ities
    0.27
    /il
    0.26
    mente
    0.22
    /un
    0.21
    lic
    0.21
    ITY
    0.20
    æĢ§çļĦ
    0.19
    bers
    0.19
    /non
    0.19
    -looking
    0.18
    Activations Density 0.011%

    No Known Activations