© 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. 756
    Prev
    Next
    INDEX
    Explanations

    thing followed by prepositions

    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
    æľŁåĨħ
    -0.21
     ÐIJлекÑģан
    -0.21
     ÐĶмиÑĤÑĢ
    -0.20
    袱
    -0.20
    plen
    -0.20
    åħ¶å®ĥéĹ®é¢ĺ
    -0.20
     ÐŁÐ¾Ñĩем
    -0.19
    ä¹ĭåĬ¿
    -0.18
    çĿĢä»ĸ
    -0.18
    ñas
    -0.17
    POSITIVE LOGITS
    ummy
    0.26
    uality
    0.26
    ality
    0.24
    /people
    0.24
    eger
    0.23
    eil
    0.23
    nels
    0.23
    ially
    0.22
    elves
    0.22
    ¸
    0.22
    Activations Density 0.043%

    No Known Activations