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. 11-TRANSCODER-HP
    4. 126009
    Prev
    Next
    INDEX
    Explanations

    ram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Seriously
    -0.29
    åħ¬æ°ij
    -0.28
     openly
    -0.27
    åºĵ
    -0.26
    èĤĭ
    -0.26
    пов
    -0.26
     Consequently
    -0.26
    èĪį
    -0.25
    _gate
    -0.25
    .requireNonNull
    -0.24
    POSITIVE LOGITS
    -ish
    0.29
    alytics
    0.27
    nable
    0.27
    人æŃ»äº¡
    0.27
    -sided
    0.27
    ishing
    0.27
    ish
    0.26
    OME
    0.26
    kim
    0.25
     familiar
    0.25
    Activations Density 2.279%

    No Known Activations