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. 27-TRANSCODER-HP
    4. 988
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķĻ
    -0.26
    levator
    -0.26
    sett
    -0.25
    读æĩĤ
    -0.25
    otation
    -0.25
     settled
    -0.25
     Höhe
    -0.24
    бÑĭ
    -0.24
     settles
    -0.24
    ffffff
    -0.24
    POSITIVE LOGITS
    ritis
    0.35
    etto
    0.27
    éric
    0.26
    erc
    0.26
    RITE
    0.25
     poss
    0.25
    ÎĨ
    0.24
    egis
    0.24
    çΏå¦Ī
    0.24
    rax
    0.24
    Activations Density 0.009%

    No Known Activations