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. 1718
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ger
    -0.26
    ensely
    -0.26
    å¦Ĥæľīä¾µæĿĥ
    -0.26
    éĢĤåºĶ
    -0.26
     porter
    -0.25
    enery
    -0.24
    ETYPE
    -0.24
    éľĪ
    -0.24
    klass
    -0.24
    cling
    -0.24
    POSITIVE LOGITS
     sol
    0.26
     solvent
    0.24
    sol
    0.24
    è°Ľ
    0.24
    osomal
    0.23
    kit
    0.23
    etail
    0.23
     series
    0.23
    èĥ´
    0.23
     Been
    0.23
    Activations Density 0.003%

    No Known Activations