© 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. 32-TRANSCODER-HP
    7. 41251
    Prev
    Next
    INDEX
    Explanations

    Genetic/biological study

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç§ĭ
    -0.31
    /link
    -0.26
     population
    -0.26
    人åı£
    -0.26
    åºĩ
    -0.25
    çŃĴ
    -0.25
    常è¯Ĩ
    -0.25
     insert
    -0.25
    yntax
    -0.25
     undertaking
    -0.25
    POSITIVE LOGITS
     base
    0.39
    base
    0.36
     Base
    0.36
    ãĥĻãĥ¼ãĤ¹
    0.34
    loc
    0.33
    locs
    0.33
    mer
    0.33
    trait
    0.33
     mer
    0.32
     loc
    0.32
    Activations Density 0.011%

    No Known Activations