© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53394
    Prev
    Next
    INDEX
    Explanations

    Code, math, biology text

    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
    afil
    -0.30
     mint
    -0.29
    aec
    -0.29
    .CreateInstance
    -0.27
    PRESSION
    -0.26
     sæ
    -0.25
    ynet
    -0.25
    çĩİ
    -0.24
    LAY
    -0.24
    mint
    -0.24
    POSITIVE LOGITS
    ere
    0.35
    éĥ½ä¸įèĥ½
    0.29
    lane
    0.29
    es
    0.28
    vo
    0.26
     Skate
    0.25
    ç®Ģ
    0.25
    á¸
    0.25
    ka
    0.25
    ç¨ĭåºı
    0.25
    Activations Density 0.003%

    No Known Activations