© 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. 9807
    Prev
    Next
    INDEX
    Explanations

    binary numbers

    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
     POINTER
    -0.31
     Cursors
    -0.28
    ><![
    -0.27
    anes
    -0.27
    enos
    -0.24
     driveway
    -0.24
    DNA
    -0.24
    ITS
    -0.24
     concent
    -0.23
     bes
    -0.23
    POSITIVE LOGITS
     Till
    0.26
    organization
    0.26
    对åħ¬åı¸
    0.26
    éĶ»
    0.26
    alez
    0.25
    è§Ħ磩
    0.25
     Organization
    0.25
     organization
    0.24
     organisation
    0.24
     afterward
    0.24
    Activations Density 0.008%

    No Known Activations