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. 24383
    Prev
    Next
    INDEX
    Explanations

    Project

    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
     singly
    -0.31
    æŃ»
    -0.26
    Kir
    -0.26
    Ñģло
    -0.26
    å®ŀ
    -0.25
    夹
    -0.25
    etheless
    -0.25
    _blank
    -0.24
    ertia
    -0.24
    thon
    -0.24
    POSITIVE LOGITS
    .dy
    0.27
    Enumerable
    0.25
    :NS
    0.25
    æµĶ
    0.25
     Bundy
    0.24
    Fraction
    0.24
    .yy
    0.24
    Liked
    0.24
    fraction
    0.24
    OU
    0.23
    Activations Density 0.002%

    No Known Activations