© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12455
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

    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
    keeping
    -0.20
    kah
    -0.18
    çĶļèĩ³
    -0.18
    åĵªæĢķ
    -0.17
    UME
    -0.17
    ãģĹãĤĩãģĨ
    -0.16
    angles
    -0.16
    allis
    -0.16
    åĭĥåĭĥ
    -0.16
    çĶļèĩ³æĺ¯
    -0.16
    POSITIVE LOGITS
    reas
    0.21
    vanced
    0.20
    rog
    0.19
    /OR
    0.19
    rea
    0.19
    thal
    0.18
    rew
    0.18
    ons
    0.17
    alous
    0.17
    大家åĪĨ享
    0.17
    Activations Density 0.141%

    No Known Activations