Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 901
    Prev
    Next
    INDEX
    Explanations

    island

    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
    leston
    -0.29
    callbacks
    -0.25
    {:
    -0.24
    ä¿Ŀ管
    -0.24
    ëį°
    -0.24
    <<<<
    -0.24
    .il
    -0.23
    Owned
    -0.23
     Columns
    -0.23
     tác
    -0.23
    POSITIVE LOGITS
    èĢħçļĦ
    0.31
    iants
    0.28
    çļĦ羣å®ŀ
    0.28
    wise
    0.27
    ichtig
    0.26
    çļĦç§ĺå¯Ĩ
    0.25
    ä¸ĭå·´
    0.25
    ecs
    0.25
    rand
    0.25
    yms
    0.25
    Activations Density 0.020%

    No Known Activations