© 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. 9058
    Prev
    Next
    INDEX
    Explanations

    code snippets/random text

    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
     Although
    -0.29
    èĻ½çĦ¶
    -0.28
    Although
    -0.28
    orts
    -0.26
    (py
    -0.26
    chy
    -0.26
    ä½ķ
    -0.25
    withstanding
    -0.25
    how
    -0.25
    cpy
    -0.25
    POSITIVE LOGITS
    éĢļè¿ĩ对
    0.30
    iative
    0.29
     dedicated
    0.28
     via
    0.27
    ä»İä¸Ń
    0.25
    imizer
    0.25
    ffic
    0.25
    zl
    0.24
     they
    0.24
     through
    0.24
    Activations Density 0.000%

    No Known Activations