© 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. 31-TRANSCODER-HP
    7. 18373
    Prev
    Next
    INDEX
    Explanations

    Code and technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĮĢ
    -0.26
    /photos
    -0.26
    Injector
    -0.26
     repeating
    -0.25
    izons
    -0.25
    lement
    -0.25
     array
    -0.24
    -binary
    -0.24
    umb
    -0.24
    array
    -0.24
    POSITIVE LOGITS
    æ§ĥ
    0.28
    ç»ĵ
    0.27
    äºĨå¤ļå°ij
    0.26
    缤
    0.26
    oke
    0.26
    设æĸ½å»ºè®¾
    0.26
    çµIJ
    0.25
    isci
    0.25
    _->
    0.25
    кÑĢÑĭÑĤ
    0.25
    Activations Density 0.044%

    No Known Activations