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. 1-TRANSCODER-HP
    4. 26
    Prev
    Next
    INDEX
    Explanations

    -ization suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_1.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.1.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inis
    -0.27
    –and
    -0.27
    产åĵģè´¨éĩı
    -0.26
    abal
    -0.25
    inine
    -0.25
    ëħĢ
    -0.25
    è´¨éĩıåĴĮ
    -0.24
     eÄŁ
    -0.24
    >window
    -0.24
    olen
    -0.24
    POSITIVE LOGITS
    į°
    0.27
    áp
    0.27
     Char
    0.26
    ipur
    0.25
    CU
    0.25
    å§Ķ
    0.25
    æ´½
    0.24
    SU
    0.24
     Perm
    0.24
    mitters
    0.23
    Activations Density 20.583%

    No Known Activations