© 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. 53181
    Prev
    Next
    INDEX
    Explanations

    thin film, covers

    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
    ality
    -0.28
     unw
    -0.28
    bu
    -0.27
    journal
    -0.27
     journal
    -0.27
     thừa
    -0.27
    electron
    -0.26
    heavy
    -0.26
    ç´«å¤ĸ线
    -0.25
    blo
    -0.25
    POSITIVE LOGITS
     Paste
    0.30
     goed
    0.28
    Paste
    0.27
    VES
    0.27
    abric
    0.25
    okus
    0.25
    åĢį
    0.24
    ertype
    0.24
    actice
    0.24
    çĹĴ
    0.24
    Activations Density 0.009%

    No Known Activations