© 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. 1969
    Prev
    Next
    INDEX
    Explanations

    kick followed by other words

    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
    risk
    -0.22
    à¹Į
    -0.21
    similar
    -0.21
    ignum
    -0.20
    clinic
    -0.20
    çľ¼ç§ij
    -0.20
    ivec
    -0.20
    isko
    -0.19
    /on
    -0.19
    olist
    -0.19
    POSITIVE LOGITS
    -off
    0.24
    ðŁı»
    0.23
    å¤įèĭı
    0.23
    æºIJäºİ
    0.22
    åħ¸ç¤¼
    0.21
     tắt
    0.21
    éŃĦ
    0.21
    è¶Ł
    0.20
     off
    0.20
    -paced
    0.20
    Activations Density 0.012%

    No Known Activations