© 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. 53907
    Prev
    Next
    INDEX
    Explanations

    Fruit colors

    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
    èµĶ
    -0.27
    éĿ¢
    -0.27
    cl
    -0.27
     nú
    -0.27
    illac
    -0.27
    ixo
    -0.26
    heet
    -0.26
    mime
    -0.25
    rack
    -0.25
     kre
    -0.25
    POSITIVE LOGITS
     amb
    0.31
     f
    0.27
    row
    0.27
     row
    0.26
    æ±īè¯Ń
    0.26
    ±Ð¾ÑĤ
    0.25
    IMA
    0.25
     ok
    0.24
    éłĵ
    0.24
     work
    0.24
    Activations Density 0.006%

    No Known Activations