© 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. 11973
    Prev
    Next
    INDEX
    Explanations

    forward movement/thinking/direction

    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
    ãģķãģĦ
    -0.18
     forthcoming
    -0.17
    antor
    -0.17
    åīįè¿°
    -0.16
    oen
    -0.16
    ç»
    -0.16
    anton
    -0.16
     foregoing
    -0.16
    -vous
    -0.16
    _Framework
    -0.16
    POSITIVE LOGITS
    -thinking
    0.25
    mente
    0.23
    /back
    0.23
     лиÑĨ
    0.21
    ness
    0.21
    slashes
    0.20
    -facing
    0.20
    swith
    0.20
    most
    0.19
    ance
    0.19
    Activations Density 0.023%

    No Known Activations