© 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. 53259
    Prev
    Next
    INDEX
    Explanations

    positive qualities

    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
    å®ĥ们
    -0.28
    æĻ¯
    -0.28
     каÑĩ
    -0.27
    å®ĥ
    -0.26
    çŀ¿
    -0.26
    æľºæŀĦ
    -0.25
    è£ħ
    -0.25
     fle
    -0.25
    她们
    -0.24
    ading
    -0.23
    POSITIVE LOGITS
     extended
    0.48
     Extended
    0.40
    æīĢ示
    0.39
    延伸
    0.39
     extending
    0.39
    Extend
    0.37
     shown
    0.36
     Extend
    0.35
    Extended
    0.35
    extended
    0.35
    Activations Density 0.017%

    No Known Activations