© 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. 24-TRANSCODER-HP
    7. 149245
    Prev
    Next
    INDEX
    Explanations

    actual

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     actually
    -0.31
    _actual
    -0.28
     Actual
    -0.28
    actually
    -0.27
     actual
    -0.27
     associations
    -0.25
    èĤ¡
    -0.25
    å®ŀéĻħ
    -0.25
     Everywhere
    -0.25
    Actual
    -0.25
    POSITIVE LOGITS
    ités
    0.29
    ç»ıåİĨ
    0.28
    atoria
    0.28
    æĵįä½ľ
    0.27
    icious
    0.27
    orio
    0.26
    chief
    0.26
    though
    0.25
    Msp
    0.25
    -existing
    0.25
    Activations Density 1.391%

    No Known Activations