© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56972
    Prev
    Next
    INDEX
    Explanations

    Chem

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ervers
    -0.29
    odelist
    -0.25
    epar
    -0.25
    eworld
    -0.25
    obby
    -0.24
    åĪłéĻ¤æĪIJåĬŁ
    -0.24
     lump
    -0.24
    äººåľ¨
    -0.23
    éĩĮçļĦ
    -0.23
    under
    -0.23
    POSITIVE LOGITS
    [--
    0.32
     Regents
    0.28
    éģ£
    0.27
     Antar
    0.27
     triple
    0.26
    NOWLED
    0.26
     santa
    0.25
    èĮĥæĸĩ
    0.25
    htags
    0.25
    letics
    0.25
    Activations Density 0.012%

    No Known Activations