© 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. 27-TRANSCODER-HP
    7. 57375
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supposedly
    -0.26
    src
    -0.25
    light
    -0.25
     lu
    -0.24
     blessed
    -0.24
    bett
    -0.24
    ä¸įå¿ĺ
    -0.24
     readily
    -0.23
    YPE
    -0.23
    éķ
    -0.23
    POSITIVE LOGITS
    æģ¶åĬ£
    0.27
    继ç»Ń
    0.26
    ialized
    0.25
    ä½İä½į
    0.25
    äºı
    0.24
    æĿµ
    0.24
    ä¿ĿçķĻ
    0.24
    cust
    0.24
    æĥ°
    0.24
    è¦Ĩ
    0.24
    Activations Density 0.001%

    No Known Activations