© 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. 11534
    Prev
    Next
    INDEX
    Explanations

    access to

    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
    åıijçĥ§
    -0.20
    çĴĥ
    -0.20
    .mousePosition
    -0.20
    .edu
    -0.19
    漪
    -0.19
     Krishna
    -0.19
    çĿ«
    -0.19
    _fence
    -0.19
    çĭ¸
    -0.19
    bildung
    -0.18
    POSITIVE LOGITS
     via
    0.32
    via
    0.29
     access
    0.28
    ãĤ¢ãĤ¯ãĤ»ãĤ¹
    0.28
    (access
    0.28
    Via
    0.27
     Via
    0.26
    便æį·
    0.26
    _via
    0.25
    åı£
    0.24
    Activations Density 0.040%

    No Known Activations