© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    radio station call signs

    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
    atile
    -0.23
    讣
    -0.22
    itespace
    -0.22
    cline
    -0.21
    CONS
    -0.21
    .isNull
    -0.21
    ExceptionHandler
    -0.21
    bands
    -0.21
     sick
    -0.21
    åijĹ
    -0.21
    POSITIVE LOGITS
    äºĮåŃĹ
    0.27
    åĽĽçº§
    0.26
    iram
    0.26
     flatt
    0.25
    ä¹ĭéģĵ
    0.24
    ä¹ĭåľ°
    0.23
     Crab
    0.22
    空ä¸Ń
    0.22
    än
    0.22
     unloaded
    0.22
    Activations Density 0.182%

    No Known Activations