© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1017
    Prev
    Next
    INDEX
    Explanations

    thermal cathet er

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ificado
    -0.24
     ohio
    -0.23
     rad
    -0.22
    èĪµ
    -0.22
     Baghd
    -0.22
    æŬ
    -0.21
    è¾Ħ
    -0.21
    èĩ¼
    -0.21
    weise
    -0.21
    esModule
    -0.21
    POSITIVE LOGITS
    .imp
    0.23
    _SEQUENCE
    0.22
     Inspir
    0.22
     Insp
    0.21
    thermal
    0.21
    æĶ¶æ¬¾
    0.20
    _poly
    0.20
    kg
    0.20
    å·¨é¢Ŀ
    0.20
    (Duration
    0.20
    Activations Density 0.003%

    No Known Activations