© 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. 9391
    Prev
    Next
    INDEX
    Explanations

    similar

    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
    èµ°å¾Ĺ
    -0.28
    oplevel
    -0.27
    ked
    -0.26
    缸è¾ĥ
    -0.25
    undef
    -0.25
    ä½łä¸į
    -0.25
    PRIVATE
    -0.25
     distinguished
    -0.25
    istinguished
    -0.25
     compared
    -0.24
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.37
     how
    0.36
     what
    0.34
     How
    0.31
    ower
    0.29
     What
    0.29
    usan
    0.29
    å¦Ĥä½ķåİ»
    0.28
    it
    0.28
    How
    0.28
    Activations Density 0.014%

    No Known Activations