© 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. 10864
    Prev
    Next
    INDEX
    Explanations

    injection related words

    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
    atics
    -0.20
    chaft
    -0.20
    istic
    -0.18
     Justi
    -0.18
    æĮĿ
    -0.17
    æĺ§
    -0.17
    istics
    -0.16
    enze
    -0.16
    èĹĵ
    -0.15
    fully
    -0.15
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.25
    ables
    0.24
    tion
    0.20
    æĪ·åı£
    0.19
    l
    0.19
    lion
    0.18
    able
    0.18
    ors
    0.17
    ary
    0.17
    lah
    0.17
    Activations Density 0.033%

    No Known Activations