© 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. 109057
    Prev
    Next
    INDEX
    Explanations

    approach

    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
    æī§æķĻ
    -0.26
    ResponseType
    -0.26
    解说
    -0.25
    主ä¹īèĢħ
    -0.25
    .ua
    -0.24
    IVED
    -0.24
    structors
    -0.24
    æ´»å¾Ĺ
    -0.24
    æ¾³
    -0.24
    zers
    -0.24
    POSITIVE LOGITS
    lew
    0.28
    Ð¡ÐŁ
    0.26
    ittle
    0.25
    Ba
    0.25
    .Scheme
    0.25
     doPost
    0.24
     automatically
    0.24
    bez
    0.24
    asel
    0.24
    çķ¹
    0.24
    Activations Density 0.341%

    No Known Activations