© 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. 53898
    Prev
    Next
    INDEX
    Explanations

    resources

    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
    ç»ıæŁ¥
    -0.29
    ariat
    -0.28
     impover
    -0.27
    æ´»ä¸ĭåİ»
    -0.27
    ADM
    -0.26
    æĶ¶ç´§
    -0.26
    çīĮçħ§
    -0.26
    èĥģ
    -0.26
    ä½İä¼°
    -0.26
    æīĵåİĭ
    -0.25
    POSITIVE LOGITS
     resources
    0.45
     resource
    0.42
     Resources
    0.37
    èµĦæºIJ
    0.37
     videos
    0.36
     instructions
    0.36
     o
    0.36
     examples
    0.36
     tutorials
    0.36
     lectures
    0.35
    Activations Density 0.129%

    No Known Activations