© 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. 16846
    Prev
    Next
    INDEX
    Explanations

    forced, involuntary, compulsory

    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
    ERM
    -0.20
    alysis
    -0.20
    åı¯è§Ĥ
    -0.20
    VISIBLE
    -0.19
    çIJIJ
    -0.19
     flare
    -0.19
     Pointer
    -0.19
    èł¹
    -0.19
    åŃ°
    -0.19
     <<-
    -0.19
    POSITIVE LOGITS
    nehmer
    0.23
    强è¡Į
    0.22
    强åĪ¶
    0.22
    åĭī强
    0.20
    forced
    0.20
    inds
    0.20
    被迫
    0.19
    æłijåı¶
    0.18
     Stitch
    0.18
    ÑĢаÐ
    0.18
    Activations Density 0.014%

    No Known Activations