© 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. 707
    Prev
    Next
    INDEX
    Explanations

    successful outcomes

    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
    oogle
    -0.24
    ä¸įæ¸ħ
    -0.22
    工夫
    -0.20
    å®ŀéĻħæĥħåĨµ
    -0.20
    åĬŁå¤«
    -0.20
    Äįe
    -0.20
    ew
    -0.19
    ouver
    -0.19
    itional
    -0.19
    ting
    -0.19
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.34
    -minded
    0.26
    -looking
    0.24
     minded
    0.24
     outcome
    0.23
    -oriented
    0.23
    绩
    0.23
     albeit
    0.22
    ively
    0.22
    /power
    0.21
    Activations Density 0.040%

    No Known Activations