© 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. 53483
    Prev
    Next
    INDEX
    Explanations

    names in various contexts

    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
    éħª
    -0.27
    pga
    -0.27
    ouch
    -0.27
    ĺ认
    -0.26
     IOS
    -0.26
    âĹĪ
    -0.25
     diligence
    -0.25
    odiac
    -0.24
    inish
    -0.24
    Faces
    -0.24
    POSITIVE LOGITS
    RM
    0.25
     sen
    0.25
    KeyPressed
    0.25
    åĵģ
    0.24
     Gib
    0.24
     rak
    0.24
    .const
    0.23
    å¸Ĥ人大
    0.23
    getC
    0.23
     V
    0.23
    Activations Density 0.012%

    No Known Activations