© 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. 14-TRANSCODER-HP
    7. 41307
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icus
    -0.30
    ervers
    -0.28
    own
    -0.26
    èĬĤæ°´
    -0.26
    ADI
    -0.26
    èĬĤèĥ½
    -0.25
    thead
    -0.25
    ica
    -0.25
    intestinal
    -0.24
    unk
    -0.24
    POSITIVE LOGITS
    溢
    0.27
    å®ŀè´¨
    0.27
    åıijå±ķä¸Ń
    0.26
    大åĬĽåıijå±ķ
    0.26
    lr
    0.26
    åıijå±ķ
    0.25
    AutoSize
    0.25
    еÑĢÑĤ
    0.25
    glomer
    0.25
    pdo
    0.24
    Activations Density 0.254%

    No Known Activations