© 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. 18-TRANSCODER-HP
    7. 88943
    Prev
    Next
    INDEX
    Explanations

    forum questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    追
    -0.28
    è¿ijæľŁ
    -0.26
    TableName
    -0.26
    没æľī太大
    -0.26
    åīįä¸įä¹ħ
    -0.26
     egt
    -0.25
    _SI
    -0.25
     Ultimate
    -0.25
    ä»ĸ们éĥ½
    -0.25
    æºľ
    -0.24
    POSITIVE LOGITS
     jung
    0.28
    erial
    0.27
    ("-",
    0.26
    Dou
    0.26
    iou
    0.25
    oppers
    0.24
    /--
    0.24
    ="#"
    0.24
    undos
    0.24
    uto
    0.24
    Activations Density 0.543%

    No Known Activations