© 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. 33-TRANSCODER-HP
    7. 53619
    Prev
    Next
    INDEX
    Explanations

    cause

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TForm
    -0.34
     PROF
    -0.28
     пÑĢедоÑģÑĤавлен
    -0.27
     PROVIDED
    -0.27
    ajs
    -0.27
    -resource
    -0.26
     RESOURCE
    -0.26
     resourceId
    -0.26
    æīĢæıIJä¾ĽçļĦ
    -0.26
    æīĢæıIJä¾Ľ
    -0.26
    POSITIVE LOGITS
     both
    0.36
    ousing
    0.34
     leading
    0.34
    à¹īà¸Ļ
    0.33
     limiting
    0.33
    both
    0.31
     threatening
    0.31
    ingly
    0.30
     Leading
    0.30
     hurting
    0.30
    Activations Density 0.044%

    No Known Activations