© 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. 12877
    Prev
    Next
    INDEX
    Explanations

    hell and Satan

    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
    èĭĵ
    -0.23
    .responses
    -0.20
     buffs
    -0.19
    çĿ«
    -0.18
    æ¶ķ
    -0.18
     Snapshot
    -0.18
    åIJĽåŃIJ
    -0.18
    è°į
    -0.17
    çķĻä¸ĭäºĨ
    -0.17
    _SN
    -0.17
    POSITIVE LOGITS
    åľ°çĭ±
    0.28
    éŃĶ鬼
    0.27
    èĪ¬çļĦ
    0.25
     hell
    0.24
     Hell
    0.23
    coal
    0.21
    代çIJĨ人
    0.21
    éĻį临
    0.21
    åĮĸ身
    0.20
    hell
    0.19
    Activations Density 0.032%

    No Known Activations