© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles followed by nouns

    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
    .Pull
    -0.24
     оÑĤз
    -0.22
     metav
    -0.22
    rag
    -0.22
     equal
    -0.22
    ä¸ºæľŁ
    -0.21
     intercept
    -0.21
    -0.21
     adm
    -0.21
    è¿IJçĶ¨
    -0.21
    POSITIVE LOGITS
    anything
    0.31
     Ñĩего
    0.29
    something
    0.28
    ä»Ģä¹Īåij¢
    0.28
    omething
    0.27
    Anything
    0.26
     stuff
    0.26
     bureaucracy
    0.25
    everything
    0.25
     Humanity
    0.25
    Activations Density 0.466%

    No Known Activations