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. 98028
    Prev
    Next
    INDEX
    Explanations

    multiple

    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
    æĿ¥è®¿
    -0.28
    æī¿
    -0.27
    lse
    -0.26
     decl
    -0.26
    wing
    -0.25
    ythe
    -0.25
    ess
    -0.25
    èĤĺ
    -0.24
    ness
    -0.24
    decl
    -0.24
    POSITIVE LOGITS
    emic
    0.29
     shifted
    0.27
    交
    0.26
    emics
    0.25
    æį¢äºĨ
    0.25
    æ£Ĵ
    0.24
     Mam
    0.24
     [#
    0.24
    sheets
    0.24
     spiked
    0.24
    Activations Density 0.009%

    No Known Activations