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. 0-TRANSCODER-HP
    4. 205
    Prev
    Next
    INDEX
    Explanations

    negative emotions and elusive things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çķ´
    -0.26
    .Stdout
    -0.24
     lÃłnh
    -0.24
     Damian
    -0.23
     TY
    -0.23
    $action
    -0.23
    é©¿
    -0.23
    cly
    -0.23
    mission
    -0.23
    thon
    -0.23
    POSITIVE LOGITS
    æľĽ
    0.29
    ALT
    0.25
    ances
    0.25
     ret
    0.25
    sson
    0.24
     ÑģкаÑĩ
    0.24
    atég
    0.24
    umu
    0.23
    elt
    0.23
    hiba
    0.23
    Activations Density 7.010%

    No Known Activations