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. 46802
    Prev
    Next
    INDEX
    Explanations

    vaccine

    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
    ivant
    -0.39
    éĥ¿
    -0.29
    igy
    -0.28
    iless
    -0.27
     Destiny
    -0.27
    -groups
    -0.27
    führung
    -0.25
    çłĶç©¶åijĺ
    -0.25
    andles
    -0.24
    .fs
    -0.24
    POSITIVE LOGITS
     mine
    0.30
     Mine
    0.28
    alg
    0.27
    åĵij
    0.26
    Mine
    0.25
    iants
    0.25
    last
    0.25
    деÑĤ
    0.25
    arsi
    0.24
    approx
    0.24
    Activations Density 0.007%

    No Known Activations