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. 46798
    Prev
    Next
    INDEX
    Explanations

    viron

    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
     jurisdictions
    -0.28
     acomp
    -0.27
    å½ĵäºĭ
    -0.26
    elpers
    -0.25
    ccount
    -0.25
     BRE
    -0.24
    åIJĪè§Ħ
    -0.24
    妣
    -0.24
     Counsel
    -0.24
    ANDLE
    -0.24
    POSITIVE LOGITS
    gr
    0.27
    xcf
    0.26
    -slider
    0.26
     meaningless
    0.26
     rooted
    0.25
    ิà¸ĩ
    0.24
    esto
    0.24
    blind
    0.24
     TYPES
    0.24
     enclosing
    0.24
    Activations Density 0.127%

    No Known Activations