© 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. 1789
    Prev
    Next
    INDEX
    Explanations

    accuracy and correctness

    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
     mentality
    -0.26
    è§ĩ
    -0.25
    ByExample
    -0.24
    æĪĺçķ¥
    -0.24
    >w
    -0.22
    çĶŁæ¶¯
    -0.22
    apult
    -0.22
    pone
    -0.22
    lift
    -0.22
    ży
    -0.21
    POSITIVE LOGITS
    åı¯ä¿¡
    0.31
     correctness
    0.31
     barring
    0.29
    ä¸į代表
    0.28
    å°½éĩı
    0.28
    å°½åĬĽ
    0.27
    hopefully
    0.26
    åı¯éĿł
    0.26
    åĬĽæ±Ĥ
    0.26
     accuracy
    0.26
    Activations Density 0.032%

    No Known Activations