© 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. 35-TRANSCODER-HP
    7. 39509
    Prev
    Next
    INDEX
    Explanations

    coding Q&A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼°
    -0.27
    æķ´æ´ģ
    -0.27
    åĴ«
    -0.26
    mlink
    -0.25
    orris
    -0.25
     iss
    -0.24
    DefaultValue
    -0.24
    employment
    -0.24
    good
    -0.24
    hipster
    -0.24
    POSITIVE LOGITS
    oth
    0.28
    aben
    0.28
    win
    0.27
     Nob
    0.27
    ac
    0.27
     win
    0.26
    Presentation
    0.26
    ab
    0.25
    ase
    0.25
     kab
    0.25
    Activations Density 84.566%

    No Known Activations