© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    give, address, be, targeted

    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
    æī¶
    -0.23
    iper
    -0.21
    amp
    -0.20
    Âł
    -0.20
     ‘
    -0.20
    æĺķ
    -0.19
    wide
    -0.18
    oct
    -0.18
    彤
    -0.18
    NotSupportedException
    -0.18
    POSITIVE LOGITS
     Redistributions
    0.23
     RETURNS
    0.20
    èĢĮæĺ¯
    0.19
    çĬĬ
    0.19
    MOTE
    0.19
    reon
    0.18
    åѦ龸
    0.18
    ØŁ
    0.18
    å½ĵä»ĸ
    0.18
     CDDL
    0.18
    Activations Density 0.293%

    No Known Activations