© 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. 25-TRANSCODER-HP
    7. 107421
    Prev
    Next
    INDEX
    Explanations

    [@

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢĤ“
    -0.31
    ï¼Į“
    -0.30
    ãĢģ“
    -0.28
    ’↵↵
    -0.27
    ï¼ļ“
    -0.27
    ãĢĤ”↵↵
    -0.26
    ”ï¼Į
    -0.25
    Matchers
    -0.25
    ’,
    -0.25
    abis
    -0.25
    POSITIVE LOGITS
    uario
    0.30
     trials
    0.27
    egr
    0.26
     оÑģновном
    0.26
    è¿«
    0.26
    æĬ¤çħ§
    0.26
    .rawValue
    0.24
     obliv
    0.24
    van
    0.24
     Passport
    0.24
    Activations Density 0.702%

    No Known Activations