© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    batting / batter / bytes

    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
    å±ĭ顶
    -0.24
     map
    -0.22
     hats
    -0.21
     overlapping
    -0.21
     arbit
    -0.20
    Map
    -0.20
    ribbon
    -0.20
    åľ°åĽ¾
    -0.20
    AMENT
    -0.20
     uplift
    -0.20
    POSITIVE LOGITS
    WithValue
    0.25
    worthy
    0.24
    们éĥ½
    0.24
    oken
    0.23
    ibles
    0.23
    éĻĮçĶŁäºº
    0.23
    ents
    0.23
    outs
    0.22
     ÑģÑĤо
    0.22
    loid
    0.22
    Activations Density 0.001%

    No Known Activations