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. 53887
    Prev
    Next
    INDEX
    Explanations

    sentence fragment

    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
    åı¯è§Ĥ
    -0.31
    çĿ¹
    -0.28
    èĽĽ
    -0.26
    åĨ³è®®
    -0.26
     enticing
    -0.26
    -tm
    -0.26
    Ñģо
    -0.25
     ICommand
    -0.24
     insanity
    -0.24
     <$
    -0.24
    POSITIVE LOGITS
    è¾¹
    0.28
    ternal
    0.26
    /OR
    0.25
    estic
    0.25
    vised
    0.24
    bjerg
    0.24
    oud
    0.24
    phies
    0.24
    å¡ŀ
    0.24
    umbled
    0.23
    Activations Density 0.027%

    No Known Activations