© 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. 795
    Prev
    Next
    INDEX
    Explanations

    damage and injury

    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
    空åīį
    -0.28
     credible
    -0.25
     fit
    -0.24
    æľīè¶³å¤ŁçļĦ
    -0.24
    coder
    -0.24
    æŶéļĶ
    -0.24
    éģĩåĪ°äºĨ
    -0.23
    former
    -0.23
    å®Įæķ´
    -0.23
    åīįæīĢæľªæľī
    -0.23
    POSITIVE LOGITS
     unnecessarily
    0.40
     unwanted
    0.38
     unnecessary
    0.35
    ä¸įå¿ħè¦ģçļĦ
    0.34
     undesirable
    0.31
    åĬ©éķ¿
    0.30
    éĢłæĪIJçļĦ
    0.30
    严éĩįå½±åĵį
    0.30
    è¿ĩå¤ļ
    0.29
     nuisance
    0.28
    Activations Density 0.470%

    No Known Activations