© 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. 54069
    Prev
    Next
    INDEX
    Explanations

    computer code and networking

    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
    atori
    -0.27
    quals
    -0.26
    iden
    -0.26
     covering
    -0.25
     xlink
    -0.25
    æ¢ģ
    -0.25
    Å©
    -0.25
    xDC
    -0.25
    ines
    -0.24
     reverse
    -0.24
    POSITIVE LOGITS
    å¤§åĽ½
    0.26
     extras
    0.26
    èĪŁ
    0.26
    ])+
    0.25
    )const
    0.25
     egt
    0.24
    æĪijè¿ĺæĺ¯
    0.24
    ibble
    0.24
    æĪijéĥ½
    0.24
    æı
    0.24
    Activations Density 0.009%

    No Known Activations