© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    angle and degrees

    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
    REAM
    -0.26
    bytes
    -0.24
    æī©å®¹
    -0.24
     junit
    -0.23
    weigh
    -0.23
    大æī¹
    -0.23
     disposable
    -0.22
     Bytes
    -0.22
     rushed
    -0.22
     Sound
    -0.22
    POSITIVE LOGITS
     angle
    0.80
    è§Ĵ度
    0.75
     angles
    0.75
    Angle
    0.68
    -angle
    0.67
    angle
    0.66
     Angle
    0.65
    (angle
    0.64
    _angle
    0.63
    çļĦè§Ĵ度
    0.60
    Activations Density 0.178%

    No Known Activations