© 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. 57866
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Ep
    -0.28
    chi
    -0.27
    åĵ¥åĵ¥
    -0.26
    纤
    -0.26
    åĦĴ
    -0.25
    abella
    -0.24
    _ENV
    -0.24
    à¸Ĺาà¸ĩ
    -0.24
    HL
    -0.24
     invers
    -0.24
    POSITIVE LOGITS
    åĮĹè·¯
    0.30
     particular
    0.29
     particul
    0.28
    è®®é¢ĺ
    0.27
     processes
    0.26
     objects
    0.26
     PARTICULAR
    0.26
    iences
    0.26
    vehicles
    0.26
     hẹn
    0.26
    Activations Density 0.001%

    No Known Activations