© 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. 151139
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ache
    -0.29
    ardless
    -0.27
     cazzo
    -0.25
    aches
    -0.25
    åī¯å¸Ĥéķ¿
    -0.24
    ivic
    -0.24
    ħĮ
    -0.24
    #region
    -0.24
    arsers
    -0.24
    Į¨
    -0.24
    POSITIVE LOGITS
     (
    0.62
    (
    0.47
     (âĪ
    0.45
    ï¼Ī
    0.42
     (£
    0.41
     (.
    0.38
     (~
    0.37
     (-
    0.36
     ($
    0.35
     (--
    0.35
    Activations Density 0.133%

    No Known Activations