© 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. 33-TRANSCODER-HP
    7. 54360
    Prev
    Next
    INDEX
    Explanations

    loc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unken
    -0.31
    odka
    -0.30
    ritch
    -0.29
    echa
    -0.28
    eah
    -0.28
    chandle
    -0.28
     Constructs
    -0.26
    chod
    -0.26
    æĢı
    -0.25
    cot
    -0.25
    POSITIVE LOGITS
    o
    0.44
    ate
    0.41
    a
    0.36
    i
    0.35
    аÑĤ
    0.33
    atin
    0.33
    ates
    0.32
    ಡ
    0.32
    At
    0.32
    ati
    0.31
    Activations Density 0.014%

    No Known Activations