© 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. 57605
    Prev
    Next
    INDEX
    Explanations

    references with birth and license

    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
     native
    -1.13
    native
    -1.01
     Native
    -0.86
    -native
    -0.86
     natives
    -0.84
    Native
    -0.81
    _native
    -0.71
    .native
    -0.67
     indigenous
    -0.66
    /native
    -0.66
    POSITIVE LOGITS
    :hidden
    0.31
    ýt
    0.26
    istance
    0.26
    peri
    0.25
    éħIJ
    0.25
    butt
    0.25
    пÑĢоÑģ
    0.24
    pler
    0.24
    UDO
    0.24
    _pins
    0.24
    Activations Density 0.002%

    No Known Activations