© 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. 508
    Prev
    Next
    INDEX
    Explanations

    Sen or senior

    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
    soever
    -0.25
    ting
    -0.24
    ëģĶ
    -0.21
    ten
    -0.20
    ll
    -0.19
    tion
    -0.19
    tod
    -0.18
    uff
    -0.18
    tv
    -0.18
    使çĶ¨ç¶²è·¯
    -0.18
    POSITIVE LOGITS
    iors
    0.24
    们
    0.24
    -most
    0.24
    ../../../
    0.23
    atures
    0.22
    们çļĦ
    0.20
    lâ
    0.20
    CTOR
    0.19
    Ùij
    0.19
    æľŁåĨħ
    0.19
    Activations Density 0.040%

    No Known Activations