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. 67598
    Prev
    Next
    INDEX
    Explanations

    death

    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
    culo
    -0.26
    unan
    -0.26
    tics
    -0.26
    梧
    -0.26
    flare
    -0.26
    mostat
    -0.25
     pe
    -0.25
    filer
    -0.25
     System
    -0.24
    é«ĺå³°
    -0.24
    POSITIVE LOGITS
    LTR
    0.31
    LOY
    0.29
    engl
    0.26
    gé
    0.24
    eking
    0.24
     suicide
    0.24
    Cols
    0.23
    TableCell
    0.23
     GSM
    0.23
    çħ
    0.23
    Activations Density 0.005%

    No Known Activations