© 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. 10855
    Prev
    Next
    INDEX
    Explanations

    spice and ingredients

    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
    ility
    -0.18
    çľ¼çIJĥ
    -0.18
    ILITY
    -0.18
    onent
    -0.17
    驾é©Ń
    -0.17
    nost
    -0.17
    <?,
    -0.16
    åİ®
    -0.16
    itone
    -0.16
    aving
    -0.16
    POSITIVE LOGITS
    flat
    0.21
    rai
    0.18
    atra
    0.17
    ä½Ĩå¦Ĥæŀľ
    0.17
     sticks
    0.17
    æĽ¦
    0.17
    trap
    0.17
    æŁ±
    0.17
    stick
    0.16
     overload
    0.16
    Activations Density 0.002%

    No Known Activations