© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 259
    Prev
    Next
    INDEX
    Explanations

    ant + subsequent parts of words

    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
    pes
    -0.20
    vents
    -0.20
    иÑĢ
    -0.20
    деÑģÑıÑĤ
    -0.20
    onder
    -0.19
    NESS
    -0.19
    åłª
    -0.19
    AREN
    -0.18
    двиг
    -0.17
    人éĢī
    -0.17
    POSITIVE LOGITS
    elope
    0.33
    lify
    0.26
    werp
    0.25
    eced
    0.23
    ions
    0.23
    rodu
    0.22
    icip
    0.22
    opoulos
    0.22
    ropol
    0.21
    ialias
    0.21
    Activations Density 0.120%

    No Known Activations