© 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. 40371
    Prev
    Next
    INDEX
    Explanations

    random data and text snippets

    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
     somewhere
    -0.28
    -operator
    -0.26
     Opera
    -0.26
    æĿľåħ°
    -0.25
    Opera
    -0.25
    æķĸ
    -0.25
    游æĪıå½ĵä¸Ń
    -0.24
     nå
    -0.24
    æĹłè®ºå¦Ĥä½ķ
    -0.24
     Played
    -0.24
    POSITIVE LOGITS
    asser
    0.26
    ç½²
    0.25
    ç»Ħè£ħ
    0.25
    éĻ¤éĿŀ
    0.25
    ;y
    0.25
    grund
    0.25
    odos
    0.25
    -form
    0.25
    asu
    0.24
     Cert
    0.24
    Activations Density 0.188%

    No Known Activations