© 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. 54426
    Prev
    Next
    INDEX
    Explanations

    "ob" or "con"

    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
    åı£æ°Ķ
    -0.27
    oftware
    -0.27
    em
    -0.26
     deviations
    -0.26
    涼
    -0.25
    ãģ¾ãĤĮ
    -0.24
    iration
    -0.24
    éĻįèĩ³
    -0.24
    æIJº
    -0.24
    ynn
    -0.24
    POSITIVE LOGITS
    éĺ¶æ¢¯
    0.31
    ELS
    0.26
    bird
    0.26
    (codec
    0.25
    _DEFINED
    0.25
     lá»Ļ
    0.25
    æ´Ĺ
    0.25
     Lanka
    0.24
    tea
    0.24
     dis
    0.23
    Activations Density 0.014%

    No Known Activations