© 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. 54115
    Prev
    Next
    INDEX
    Explanations

    resin

    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
    radi
    -0.33
     radi
    -0.31
     truth
    -0.29
    æĹĹ
    -0.26
     scene
    -0.26
    æ®ĭ
    -0.26
    eneg
    -0.26
    forces
    -0.25
    PO
    -0.25
     flaming
    -0.25
    POSITIVE LOGITS
    .dirty
    0.28
    OUS
    0.28
    ocht
    0.27
    ockets
    0.26
    atisch
    0.25
    Mac
    0.24
    ç«ŀ
    0.24
    (delta
    0.24
    (drop
    0.24
    çĨĬ
    0.24
    Activations Density 0.014%

    No Known Activations