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. 130014
    Prev
    Next
    INDEX
    Explanations

    for/at

    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
    us
    -0.29
    ion
    -0.29
    alach
    -0.27
    è¿Ľåıĸ
    -0.26
    èĭij
    -0.26
    acon
    -0.26
    olute
    -0.25
    athon
    -0.25
    leta
    -0.25
    _BLEND
    -0.25
    POSITIVE LOGITS
    systems
    0.30
     operands
    0.29
    WER
    0.27
    ctal
    0.25
    æĺĤ
    0.25
    verbs
    0.25
    æ»ĥ
    0.25
    vens
    0.24
    ptions
    0.24
     Rox
    0.24
    Activations Density 0.003%

    No Known Activations