© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    abstract or symbolic qualifiers

    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¿Ļ个èģĮä¸ļ
    -0.27
    èĤ²
    -0.24
    _TUN
    -0.24
     stable
    -0.23
    adb
    -0.23
     Stable
    -0.22
     afford
    -0.21
    èĩªåѦ
    -0.21
    stable
    -0.21
     intercepted
    -0.21
    POSITIVE LOGITS
    istically
    0.27
    æķĪåºĶ
    0.27
    istic
    0.25
    éĿ¢åŃIJ
    0.25
    åľ°æłĩ
    0.24
    åĬŁå¤«
    0.24
    æĦıä¹īä¸Ĭ
    0.24
    usize
    0.23
     matters
    0.23
    _remaining
    0.23
    Activations Density 0.034%

    No Known Activations