© 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. 32-TRANSCODER-HP
    7. 43928
    Prev
    Next
    INDEX
    Explanations

    invitations or calls to action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turb
    -0.26
    ï¼ģ
    -0.25
    sov
    -0.24
    оÑĩно
    -0.24
     totalmente
    -0.24
     mandatory
    -0.24
     fark
    -0.23
     differential
    -0.23
    ietf
    -0.23
    atee
    -0.23
    POSITIVE LOGITS
     yourself
    0.38
     yours
    0.36
     your
    0.35
     Me
    0.32
    your
    0.30
     Th
    0.29
     me
    0.29
    å¯¹ä½ł
    0.29
    rase
    0.28
     th
    0.27
    Activations Density 0.006%

    No Known Activations