© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 94
    Prev
    Next
    INDEX
    Explanations

    pallet, cargo, barrels, shipping, crates

    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
    .Phone
    -0.26
    éĵŁ
    -0.25
    éķĬ
    -0.25
     jurisdiction
    -0.23
    管è¾ĸ
    -0.23
    éĴĪ
    -0.23
    _pin
    -0.23
    conj
    -0.22
    éĴ¥
    -0.22
    Interstitial
    -0.22
    POSITIVE LOGITS
    åŀĽ
    0.36
     cargo
    0.31
     crates
    0.31
    è´§è¿IJ
    0.31
    è¿IJè¾ĵ
    0.30
    è´§
    0.29
    è´§çī©
    0.29
     pallet
    0.29
     barrels
    0.28
     lumber
    0.28
    Activations Density 0.021%

    No Known Activations