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. 23-TRANSCODER-HP
    4. 798
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģéģĵ
    -0.32
    ÂŃi
    -0.27
    asan
    -0.26
    z
    -0.25
    zend
    -0.25
    ç§įç±»
    -0.24
    amar
    -0.24
    Uni
    -0.24
    wire
    -0.24
    difficulty
    -0.23
    POSITIVE LOGITS
    icut
    0.30
    ,message
    0.28
    |unique
    0.25
     predecessors
    0.25
    ramid
    0.24
     RT
    0.24
    idders
    0.24
     chopping
    0.24
    ombies
    0.24
     donors
    0.24
    Activations Density 0.800%

    No Known Activations