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. 130374
    Prev
    Next
    INDEX
    Explanations

    objects/parts

    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
    minate
    -0.28
    ritch
    -0.27
    GBT
    -0.27
    (KP
    -0.25
    çļĦæĦŁè§ī
    -0.25
    stitial
    -0.24
     naked
    -0.24
    setTitle
    -0.23
    注å°Ħ
    -0.23
    deny
    -0.23
    POSITIVE LOGITS
    ä¸Ģ头
    0.28
    åµ´
    0.27
    ef
    0.27
     alice
    0.27
    </
    0.27
    .bounds
    0.26
    大æĪĺ
    0.26
    çķ¥å¾®
    0.26
    .pe
    0.25
    alice
    0.25
    Activations Density 0.001%

    No Known Activations