© 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. 57531
    Prev
    Next
    INDEX
    Explanations

    support

    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
    berger
    -0.28
    omer
    -0.27
    gage
    -0.25
    á»ĩp
    -0.23
    enuity
    -0.23
    oran
    -0.23
    ALES
    -0.23
    aping
    -0.23
    etical
    -0.22
    ical
    -0.22
    POSITIVE LOGITS
    大å±Ģ
    0.30
    óc
    0.26
    اÙĦÙģ
    0.24
    less
    0.24
    åĮĸå¦Ĩ
    0.23
    辨
    0.23
    èĮ§
    0.23
    å±ĢéĿ¢
    0.23
    iously
    0.23
    OA
    0.23
    Activations Density 0.114%

    No Known Activations