© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16591
    Prev
    Next
    INDEX
    Explanations

    metastatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    umen
    -0.22
    osti
    -0.20
    -invalid
    -0.19
    èĿ½
    -0.18
    .INSTANCE
    -0.18
     variation
    -0.18
    BOSE
    -0.18
    akter
    -0.18
     Ñĥзн
    -0.17
    _Public
    -0.17
    POSITIVE LOGITS
    æĢ§çĸ¾çĹħ
    0.24
    转移
    0.21
    èĽŁ
    0.20
     oceans
    0.20
    -free
    0.19
     overseas
    0.18
    sit
    0.18
    ienne
    0.18
    pet
    0.18
    æī©æķ£
    0.18
    Activations Density 0.051%

    No Known Activations