© 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. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40554
    Prev
    Next
    INDEX
    Explanations

    Taxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸¤å¼ł
    -0.29
     gev
    -0.27
    dge
    -0.26
    ãĤīãģļ
    -0.26
     incur
    -0.25
    å½ĵåľ°äºº
    -0.24
    .Inv
    -0.24
    -secret
    -0.24
    æºIJæ³ī
    -0.24
     Claim
    -0.24
    POSITIVE LOGITS
     standardized
    0.27
    交æİ¥
    0.26
    æłĩåĩĨåĮĸ
    0.26
    害
    0.25
    .SpringBootTest
    0.25
    oy
    0.24
    交
    0.24
    éĽħ
    0.24
    Autom
    0.24
    .json
    0.24
    Activations Density 0.069%

    No Known Activations