© 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
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 8896
    Prev
    Next
    INDEX
    Explanations

    Scientific publications and citations

    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
    ;p
    -0.32
    ORA
    -0.27
    TERN
    -0.26
    èĥ§
    -0.26
    tring
    -0.26
    ;;;;;;;;
    -0.25
    ;i
    -0.25
    ;o
    -0.25
     freq
    -0.25
    ;;;
    -0.24
    POSITIVE LOGITS
    MF
    0.27
     addCriterion
    0.26
    è§ģè¯Ĩ
    0.26
    _mA
    0.25
     MJ
    0.25
    å®
    0.25
    arrow
    0.25
    MA
    0.24
    VB
    0.24
    ä¸Ģ头
    0.24
    Activations Density 0.017%

    No Known Activations