© 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. 14512
    Prev
    Next
    INDEX
    Explanations

    associate positions

    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
    ness
    -0.20
    set
    -0.20
    ming
    -0.18
    istic
    -0.18
    ãģĦãĤĭ
    -0.17
    speaker
    -0.17
    sse
    -0.17
    ãģıãĤĮ
    -0.17
    scape
    -0.17
    ĵ
    -0.17
    POSITIVE LOGITS
    ฯ
    0.19
    -level
    0.18
    们
    0.18
    ðŁı»
    0.17
    hood
    0.17
    们éĥ½
    0.17
    åĢij
    0.17
    innen
    0.17
    èĩ³ä¸Ĭ
    0.17
    ion
    0.16
    Activations Density 0.016%

    No Known Activations