© 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. 53478
    Prev
    Next
    INDEX
    Explanations

    Name fragments

    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
    é£İåIJ¹
    -0.29
     ped
    -0.27
    rum
    -0.25
    arend
    -0.25
    /Index
    -0.25
    marked
    -0.24
    agent
    -0.23
    ä¸ļ主
    -0.23
    æķĻèĤ²åŁ¹è®Ń
    -0.23
    豫
    -0.23
    POSITIVE LOGITS
    éĢģè¾¾
    0.30
    å°Ħ
    0.30
    pressure
    0.27
    olson
    0.26
     press
    0.25
    bite
    0.25
    æįŀ
    0.25
     lance
    0.24
    uen
    0.24
     casts
    0.24
    Activations Density 0.017%

    No Known Activations