© 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. 54397
    Prev
    Next
    INDEX
    Explanations

    the letter n

    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
    -sem
    -0.29
    Later
    -0.29
    vä
    -0.27
     vis
    -0.27
     sem
    -0.27
     tat
    -0.26
     tut
    -0.26
     elsewhere
    -0.25
     ts
    -0.25
     semi
    -0.25
    POSITIVE LOGITS
    ASH
    0.31
    ared
    0.27
     cage
    0.27
    ash
    0.26
    笼
    0.26
    aring
    0.26
    æ«ĥ
    0.25
    BL
    0.25
    ette
    0.24
    asin
    0.24
    Activations Density 0.006%

    No Known Activations