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. 783
    Prev
    Next
    INDEX
    Explanations

    that

    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
    uentes
    -0.28
    fil
    -0.28
    å͝
    -0.27
    jb
    -0.27
     hostages
    -0.27
    things
    -0.26
     cosas
    -0.26
    fig
    -0.26
    åºŃ
    -0.25
    æĥŁ
    -0.25
    POSITIVE LOGITS
     terminology
    0.35
     one
    0.33
     skeleton
    0.30
     lifestyle
    0.29
     other
    0.26
     technique
    0.26
     pair
    0.26
     wording
    0.26
     activity
    0.26
     someone
    0.26
    Activations Density 0.078%

    No Known Activations