© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    beginnings of phrases or clauses

    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
    èĥ½æ»¡è¶³
    -0.22
    htub
    -0.22
    Dirty
    -0.22
     sure
    -0.22
    颤
    -0.21
    éĥ½ä¸įä¼ļ
    -0.21
     replication
    -0.21
    rophic
    -0.20
    _bridge
    -0.20
    bler
    -0.20
    POSITIVE LOGITS
    HeaderCode
    0.25
    stand
    0.24
    angan
    0.23
    ReturnValue
    0.22
    åĨ·æ°´
    0.22
    èĭ±çī¹
    0.22
    airy
    0.21
    .DataType
    0.21
    addir
    0.21
    ç»Ī
    0.21
    Activations Density 0.080%

    No Known Activations