© 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. 1198
    Prev
    Next
    INDEX
    Explanations

    state or association

    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
     Lomb
    -0.26
    追
    -0.25
    ouro
    -0.23
    iri
    -0.22
    åĬĽäºī
    -0.22
    è¡Įäºĭ
    -0.22
    OLA
    -0.21
    讳
    -0.21
    hoc
    -0.21
    DTV
    -0.21
    POSITIVE LOGITS
    âģ
    0.23
    getBlock
    0.22
     raj
    0.21
    ·»
    0.21
     mand
    0.21
     Pig
    0.21
    isia
    0.21
    æĹ¥äº§
    0.21
     Atom
    0.21
    ]\\
    0.20
    Activations Density 0.632%

    No Known Activations