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. 72105
    Prev
    Next
    INDEX
    Explanations

    certification

    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
    jax
    -0.29
    urm
    -0.26
    apl
    -0.25
    alcon
    -0.25
     softly
    -0.24
    arden
    -0.24
     rond
    -0.24
    oux
    -0.24
    mith
    -0.24
    çĽ¸ä¼ł
    -0.24
    POSITIVE LOGITS
    ower
    0.25
     Pose
    0.25
    ä»ĸèĩªå·±
    0.25
     literals
    0.24
    imonials
    0.24
    _graphics
    0.24
    ftime
    0.23
    -Series
    0.23
     Tribune
    0.23
    åĥŃ
    0.23
    Activations Density 0.003%

    No Known Activations