© 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. 22-TRANSCODER-HP
    7. 88176
    Prev
    Next
    INDEX
    Explanations

    Professions and related roles

    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
    nge
    -0.28
    iam
    -0.27
     Replies
    -0.25
    ãĤ¹ãĤŃ
    -0.25
    ales
    -0.25
    ç¬Ķ
    -0.24
    ale
    -0.24
    ì¡°
    -0.24
     piano
    -0.24
    nh
    -0.24
    POSITIVE LOGITS
    anko
    0.27
    ulled
    0.26
    æĺ¯çľŁçļĦ
    0.25
     Closet
    0.25
    ücken
    0.25
    XD
    0.25
    红æĹĹ
    0.24
    addin
    0.24
    becue
    0.24
    ocrats
    0.24
    Activations Density 0.014%

    No Known Activations