© 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. 33-TRANSCODER-HP
    7. 53920
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    马
    -0.27
    çļĦæľĢä½³
    -0.26
     dop
    -0.25
    馬
    -0.24
    fol
    -0.24
     PM
    -0.24
    åĽ´æ£ĭ
    -0.24
    Lean
    -0.23
    naz
    -0.23
    液
    -0.23
    POSITIVE LOGITS
    itics
    0.26
    iators
    0.25
    -ios
    0.24
    andes
    0.24
    XObject
    0.24
    ç±´
    0.23
    cj
    0.23
    istine
    0.23
    irth
    0.23
    acho
    0.23
    Activations Density 0.008%

    No Known Activations