© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1483
    Prev
    Next
    INDEX
    Explanations

    free software

    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
     remark
    -0.27
     Emp
    -0.23
    RESS
    -0.23
    ç»ħ
    -0.23
    press
    -0.22
     Remark
    -0.22
     Empire
    -0.22
    PRESS
    -0.22
    pressions
    -0.21
    å¸ĿåĽ½
    -0.21
    POSITIVE LOGITS
     paving
    0.23
     Nun
    0.23
    _det
    0.22
    iquer
    0.22
     TOUR
    0.21
    joy
    0.21
    ç®´
    0.21
    zone
    0.20
    çĶŁæ´»çݯå¢ĥ
    0.20
    ichel
    0.20
    Activations Density 0.007%

    No Known Activations