© 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. 569
    Prev
    Next
    INDEX
    Explanations

    SUV and off-road vehicles

    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
     assassination
    -0.28
     piano
    -0.27
     Piano
    -0.26
    å¼ij
    -0.26
    æĶ¶çĽĺ
    -0.25
    ç³ł
    -0.25
     assass
    -0.25
    大楼
    -0.24
    ä¹Ĵä¹ĵçIJĥ
    -0.24
     murdered
    -0.23
    POSITIVE LOGITS
    è¶Ĭéĩİ
    0.60
    éĩİå¤ĸ
    0.49
     rugged
    0.44
    è·¯åĨµ
    0.38
     jeep
    0.38
     Jeep
    0.36
    éĩİ
    0.35
     muddy
    0.34
    èĩªé©¾
    0.34
     trek
    0.33
    Activations Density 0.058%

    No Known Activations