© 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. 54088
    Prev
    Next
    INDEX
    Explanations

    Chemistry/scientific research

    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
     enabled
    -0.26
    etration
    -0.26
    ilda
    -0.25
    æ¶ĤæĬ¹
    -0.25
    å¿ĥå¢ĥ
    -0.25
     pillows
    -0.24
     touched
    -0.24
    webdriver
    -0.24
    -touch
    -0.24
    _tick
    -0.24
    POSITIVE LOGITS
    äºĭåĬ¡
    0.29
    .transitions
    0.27
     IPS
    0.27
    åīįèĢħ
    0.26
    tras
    0.25
    idth
    0.25
     transition
    0.25
    æľīèī²
    0.25
    æIJŀ好
    0.24
    pany
    0.24
    Activations Density 0.031%

    No Known Activations