© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2640
    Prev
    Next
    INDEX
    Explanations

    solve problems or find functions

    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
    åĻ«
    -0.26
    产ä¸ļéĵ¾
    -0.25
    _CLR
    -0.24
    IMIT
    -0.23
    çļĦçĶŁæ´»
    -0.23
     Ba
    -0.23
    _OBS
    -0.22
    åºķå±Ĥ
    -0.22
    ULL
    -0.22
     VS
    -0.22
    POSITIVE LOGITS
    è§£çŃĶ
    0.41
    è§£
    0.34
     solution
    0.33
     solves
    0.33
     solving
    0.32
     solução
    0.32
    满足
    0.32
     solutions
    0.32
     solved
    0.31
     rozwiÄħz
    0.31
    Activations Density 0.449%

    No Known Activations