© 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. 27-TRANSCODER-HP
    7. 8123
    Prev
    Next
    INDEX
    Explanations

    Nor

    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
    .isNull
    -0.26
    çĨŁç»ĥ
    -0.26
    rop
    -0.26
    æ£Ģç´¢
    -0.26
    积æŀģæݢ索
    -0.25
    decltype
    -0.25
    isplay
    -0.24
    çĶº
    -0.24
    åªĴ
    -0.24
    åĸĤ
    -0.24
    POSITIVE LOGITS
     ÑģÑĤоим
    0.28
    æĶ¶çº³
    0.25
     DOT
    0.25
    odo
    0.24
    nde
    0.24
    .accept
    0.24
    IEEE
    0.23
     intr
    0.23
    halten
    0.23
    å°Ĭ
    0.23
    Activations Density 0.953%

    No Known Activations