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. 716
    Prev
    Next
    INDEX
    Explanations

    co

    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
     fam
    -0.30
    éĺ¶çº§
    -0.29
     dest
    -0.27
     Sr
    -0.26
    éĺ¶å±Ĥ
    -0.26
    avad
    -0.25
    edImage
    -0.25
    çѾ
    -0.25
     grand
    -0.24
    ato
    -0.24
    POSITIVE LOGITS
    ĥģ
    0.26
    绿è±Ĩ
    0.26
    >window
    0.26
    EMS
    0.25
    onclick
    0.25
    venta
    0.25
    hog
    0.24
     //#
    0.24
     anale
    0.24
    onth
    0.24
    Activations Density 0.014%

    No Known Activations