© 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. 11778
    Prev
    Next
    INDEX
    Explanations

    female characters and relationships

    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
    çĮĽ
    -0.22
    åı£åı·
    -0.22
    æŃĥ
    -0.22
    æļ´åĬĽ
    -0.21
    åħ¨çIJĥ
    -0.21
     operational
    -0.21
     genesis
    -0.21
    èĢģåŃIJ
    -0.20
    äºī龸
    -0.20
    digital
    -0.20
    POSITIVE LOGITS
     sourceMapping
    0.26
    ledon
    0.26
    combe
    0.24
    ·»
    0.24
    _lazy
    0.23
    æĢ§æł¼
    0.23
    SSIP
    0.22
    "urls
    0.22
    incare
    0.22
     gossip
    0.21
    Activations Density 0.032%

    No Known Activations