© 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. 35-TRANSCODER-HP
    7. 39817
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oose
    -0.31
     obstacles
    -0.25
    оÑģÑĮ
    -0.24
    .hits
    -0.24
    ãĤ´ãĥ¼ãĥ«
    -0.23
    ä¸İä¸ŃåĽ½
    -0.23
    arte
    -0.23
    éĹ®æĪij
    -0.23
    icast
    -0.22
    è¢Ńåĩ»
    -0.22
    POSITIVE LOGITS
    line
    0.30
    second
    0.28
    now
    0.28
    ubit
    0.27
    prep
    0.27
    äºĮ线
    0.27
    mens
    0.27
    specific
    0.26
    éĿŀ
    0.25
    æĹĹ
    0.25
    Activations Density 1.750%

    No Known Activations