© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2155
    Prev
    Next
    INDEX
    Explanations

    resetting password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    è´¯
    -0.24
    Lat
    -0.23
    æĶ¿æ³ķ
    -0.22
    æŶè£ħ
    -0.22
    çĤĴä½ľ
    -0.22
    TouchListener
    -0.22
    åħĭæĸ¯
    -0.22
    è¦ı模
    -0.21
    [count
    -0.21
    绣çŃ¹
    -0.21
    POSITIVE LOGITS
     Restore
    0.32
     Password
    0.31
     restoration
    0.29
    沦
    0.29
     restore
    0.28
    æī¾åĽŀ
    0.27
    -password
    0.27
     password
    0.27
    æģ¢å¤į
    0.27
     restoring
    0.27
    Activations Density 0.011%

    No Known Activations