© 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. 22-TRANSCODER-HP
    7. 111302
    Prev
    Next
    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angers
    -0.28
    sit
    -0.27
    è¿Ļä¹Īåģļ
    -0.27
    ảng
    -0.26
    äºĤ
    -0.26
    ä¸ĩä¸Ģ
    -0.25
    csrf
    -0.25
     complication
    -0.25
    ausal
    -0.25
    tober
    -0.25
    POSITIVE LOGITS
    zelf
    0.27
     EINA
    0.25
     anal
    0.25
     algun
    0.25
    ctor
    0.24
    emand
    0.24
    igne
    0.24
     He
    0.24
     MH
    0.24
    ron
    0.24
    Activations Density 0.010%

    No Known Activations