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. 11-TRANSCODER-HP
    4. 46275
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĭå®ŀ
    -0.28
    tid
    -0.27
    çļĦäºĭå®ŀ
    -0.26
    ä¸įçķĻ
    -0.26
    åIJĪéĢĤ
    -0.26
     fixed
    -0.24
    'im
    -0.24
    .gold
    -0.24
    imp
    -0.24
     fact
    -0.23
    POSITIVE LOGITS
    åı¯è§Ĥ
    0.30
     cheeses
    0.29
    homes
    0.29
    juan
    0.27
    olson
    0.26
     homes
    0.25
     activ
    0.25
     needles
    0.25
     chees
    0.24
    .activate
    0.24
    Activations Density 0.187%

    No Known Activations