© 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. 54189
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     backs
    -0.28
     tic
    -0.27
     sp
    -0.27
    ifers
    -0.26
    headers
    -0.26
    -guard
    -0.25
     router
    -0.25
    Languages
    -0.25
    eno
    -0.24
    éĥ¡
    -0.24
    POSITIVE LOGITS
    åĽĽçº§
    0.28
    hal
    0.26
    inite
    0.26
    æĭį
    0.26
     ball
    0.26
    çIJĥ
    0.26
    ä¸Ģ级
    0.26
    ball
    0.26
    .band
    0.25
     Mali
    0.24
    Activations Density 0.003%

    No Known Activations