© 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. 594
    Prev
    Next
    INDEX
    Explanations

    Assad, Malala, Damascus, Q

    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
    ç¬ı
    -0.23
    ponse
    -0.22
    åľ°è¯´
    -0.20
    ('').
    -0.20
     NONE
    -0.20
     tally
    -0.20
     Bucket
    -0.19
    è¾ĺ
    -0.19
    è¤Ĭ
    -0.19
    .isTrue
    -0.19
    POSITIVE LOGITS
    iming
    0.23
    åĪ©äºļ
    0.21
    erot
    0.21
    XR
    0.21
    azine
    0.20
    ä½ĵç³»
    0.20
    sonian
    0.20
    iteur
    0.20
    Means
    0.20
    adians
    0.20
    Activations Density 0.003%

    No Known Activations