© 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. 22-TRANSCODER-HP
    7. 112792
    Prev
    Next
    INDEX
    Explanations

    Freedom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.26
    大家åĪĨ享
    -0.25
    çŃīå½¢å¼ı
    -0.25
    æĪijçŁ¥éģĵ
    -0.25
    udes
    -0.23
    anner
    -0.23
    anners
    -0.23
    æĦıæĥ³ä¸įåĪ°
    -0.23
    etz
    -0.23
    è¡£
    -0.23
    POSITIVE LOGITS
     transition
    0.26
    transition
    0.26
    oli
    0.25
    çois
    0.24
    -opt
    0.24
    æIJĢ
    0.24
    :error
    0.23
    绿èī²åıijå±ķ
    0.23
    /MIT
    0.23
    around
    0.23
    Activations Density 0.003%

    No Known Activations