© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 848
    Prev
    Next
    INDEX
    Explanations

    forgetting things

    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
    ä¸ĩå¤ļ
    -0.20
    akte
    -0.20
    hattan
    -0.19
    ikes
    -0.18
    说æ³ķ
    -0.18
    ä¸Ģçķª
    -0.18
    ä¸įä½³
    -0.18
    itet
    -0.18
    -0.18
    åijĺ
    -0.17
    POSITIVE LOGITS
    ably
    0.31
    ful
    0.25
    æİī
    0.24
    fulness
    0.22
    edly
    0.21
    ting
    0.21
    /not
    0.21
    äºĨå¾Īå¤ļ
    0.20
    /remove
    0.20
    ä¸Ģ件äºĭ
    0.20
    Activations Density 0.010%

    No Known Activations