© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12528
    Prev
    Next
    INDEX
    Explanations

    file and network handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    kest
    -0.20
    holes
    -0.19
    ogan
    -0.19
    vara
    -0.18
    æľīçĤ¹
    -0.18
     Ùĥب
    -0.18
    dim
    -0.18
    гал
    -0.18
    afs
    -0.17
    arda
    -0.17
    POSITIVE LOGITS
    webElementProperties
    0.25
     principalTable
    0.22
    webElementXpaths
    0.22
    PullParser
    0.20
    _MetaData
    0.20
    SetBranchAddress
    0.20
    	RTLR
    0.20
    çıłæ±Ł
    0.19
    ä»»åij½
    0.19
    _ComCallableWrapper
    0.19
    Activations Density 0.598%

    No Known Activations