© 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. 57562
    Prev
    Next
    INDEX
    Explanations

    alive

    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
    reso
    -0.29
    StateException
    -0.28
     Greene
    -0.26
    direction
    -0.25
    uality
    -0.25
    awe
    -0.25
    ptype
    -0.24
    seite
    -0.24
    ovation
    -0.24
    series
    -0.24
    POSITIVE LOGITS
    aky
    0.25
     dur
    0.25
     payable
    0.24
    rut
    0.24
    _frm
    0.24
     вн
    0.24
    ORY
    0.23
    kir
    0.23
    ufact
    0.23
    ãģĵãģ¨ãģ§
    0.23
    Activations Density 0.022%

    No Known Activations