© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54479
    Prev
    Next
    INDEX
    Explanations

    should/please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penalties
    -0.26
    onnen
    -0.25
    itra
    -0.24
    filer
    -0.24
    dra
    -0.23
    æijĩ头
    -0.23
     newPath
    -0.23
    çļĦçIJĨçĶ±
    -0.23
    tu
    -0.23
    <LM
    -0.23
    POSITIVE LOGITS
    ä¸įå°ijäºİ
    0.29
    éļı
    0.28
     not
    0.27
    oyo
    0.26
     NOT
    0.26
     Follow
    0.26
    Follow
    0.26
    BAT
    0.26
    æķĻèĤ²
    0.25
     Reno
    0.25
    Activations Density 0.023%

    No Known Activations