© 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. 35-TRANSCODER-HP
    7. 39066
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nine
    -0.48
     eight
    -0.46
     Eight
    -0.45
    ä¹Ŀ
    -0.45
     ninth
    -0.43
    第ä¹Ŀ
    -0.43
    eight
    -0.42
    åħ«
    -0.41
     Nine
    -0.41
    第åħ«
    -0.40
    POSITIVE LOGITS
    5
    0.79
    6
    0.77
    ï¼ĸ
    0.63
    ï¼ķ
    0.63
     five
    0.58
    äºĶåħŃ
    0.57
     sixth
    0.57
     six
    0.55
     SIX
    0.55
     fifth
    0.53
    Activations Density 71.395%

    No Known Activations