© 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. 58034
    Prev
    Next
    INDEX
    Explanations

    Code and various subjects

    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
    series
    -0.25
    Ãłi
    -0.24
    cmp
    -0.24
    astery
    -0.23
    illing
    -0.23
    aby
    -0.23
    æĪĺæľº
    -0.23
    è°Ĭ
    -0.23
    ocator
    -0.23
    ivable
    -0.22
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.33
     stem
    0.30
    _TYPEDEF
    0.30
     manifest
    0.28
    hq
    0.28
    lte
    0.27
     itself
    0.27
     affected
    0.27
    Ĥæķ°
    0.26
    ä¹Łéļıä¹ĭ
    0.26
    Activations Density 0.008%

    No Known Activations