© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    of

    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
    è¶ħè¶Ĭ
    -0.26
    location
    -0.25
    ä¸Ńå°ıåŀĭ
    -0.24
    FIELDS
    -0.24
    fé
    -0.24
    NSE
    -0.24
    åŃĹåı·
    -0.23
    LOCATION
    -0.23
    é¦ĸ缸
    -0.23
    ç»ķ
    -0.23
    POSITIVE LOGITS
    geben
    0.26
    ivers
    0.25
    anje
    0.25
    ág
    0.24
    icol
    0.24
    ÃŃstica
    0.24
    esz
    0.24
     tolerant
    0.24
    igrams
    0.23
     cheapest
    0.23
    Activations Density 0.017%

    No Known Activations