© 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. 14545
    Prev
    Next
    INDEX
    Explanations

    shipwreck or wreck

    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
    /OR
    -0.17
    encing
    -0.16
    æı®
    -0.16
     лиÑĨа
    -0.16
    à¹Ħหว
    -0.16
    ilty
    -0.15
    çĪĨ款
    -0.15
    nal
    -0.15
    ê»ĺ
    -0.15
    enko
    -0.15
    POSITIVE LOGITS
     havoc
    0.26
    abil
    0.21
    edException
    0.20
    åħ®
    0.19
    oes
    0.19
    оп
    0.19
    alls
    0.19
    cies
    0.19
    ingly
    0.18
    าะ
    0.18
    Activations Density 0.009%

    No Known Activations