© 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. 1622
    Prev
    Next
    INDEX
    Explanations

    cue for information or action

    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
    ially
    -0.22
    -minded
    -0.21
     exceedingly
    -0.21
    uous
    -0.21
    еÑĨ
    -0.20
    éĤij
    -0.20
    omorphic
    -0.20
    ES
    -0.19
    cope
    -0.19
    ION
    -0.19
    POSITIVE LOGITS
    åįģ足
    0.23
    pha
    0.22
    gle
    0.21
    æľ¬èĥ½
    0.20
    éĿŀ常æĺİæĺ¾
    0.20
    ing
    0.20
    äºĨä¸Ģ声
    0.20
    èĩ¾
    0.20
    绳
    0.19
    een
    0.19
    Activations Density 0.005%

    No Known Activations