© 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. 56447
    Prev
    Next
    INDEX
    Explanations

    point of view

    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
    Negative Logits
     sorts
    -0.26
     Upper
    -0.26
     replication
    -0.24
     Stateless
    -0.24
    	diff
    -0.24
    lj
    -0.24
     ê
    -0.23
     tắc
    -0.23
    uju
    -0.23
    RIX
    -0.23
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.28
    äººæł¼
    0.28
    itere
    0.27
    nan
    0.26
    kit
    0.26
     retrieved
    0.26
    ackbar
    0.25
    ÑĤан
    0.25
    为æ°ij
    0.25
    phas
    0.25
    Activations Density 0.003%

    No Known Activations