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. 7-TRANSCODER-HP
    4. 93038
    Prev
    Next
    INDEX
    Explanations

    Mississippi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssi
    -0.28
     termin
    -0.26
    ии
    -0.26
    opolitan
    -0.25
    Enums
    -0.24
    ableObject
    -0.24
     Bash
    -0.24
     Pai
    -0.24
    bidden
    -0.24
    åıĤ
    -0.23
    POSITIVE LOGITS
    elage
    0.25
     jal
    0.25
     Simmons
    0.25
     TF
    0.25
     profile
    0.24
    imore
    0.24
     Fol
    0.24
    rawer
    0.24
    greater
    0.24
    made
    0.23
    Activations Density 0.785%

    No Known Activations