© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7986
    Prev
    Next
    INDEX
    Explanations

    .g

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spheres
    -0.28
    kea
    -0.28
     pinch
    -0.27
     concentration
    -0.27
     correspond
    -0.26
    æ®·
    -0.26
    gün
    -0.26
    åºĦ
    -0.26
    getSource
    -0.25
     ready
    -0.25
    POSITIVE LOGITS
    gress
    0.26
     ['$
    0.25
    ales
    0.24
    iter
    0.24
    詹å§Ĩ
    0.24
    ess
    0.24
    æ¶Īè´¹èĢħ
    0.24
    åħ³äºİæĪij们
    0.24
    ä¸Ģç±»
    0.24
    ames
    0.23
    Activations Density 0.092%

    No Known Activations