© 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. 12886
    Prev
    Next
    INDEX
    Explanations

    deploying software or systems

    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
    berger
    -0.20
    hood
    -0.17
    bild
    -0.16
    folk
    -0.16
    ç½ijé¦ĸ页
    -0.16
    -paced
    -0.16
    istic
    -0.15
    è··
    -0.15
    SHIP
    -0.15
    untime
    -0.15
    POSITIVE LOGITS
    ments
    0.26
    able
    0.22
    èĩªå¦Ĥ
    0.21
    MENT
    0.20
    ables
    0.18
    âį¨
    0.17
    åĪ°ä½į
    0.17
    ability
    0.17
     Brend
    0.17
    ment
    0.17
    Activations Density 0.020%

    No Known Activations