© 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. 54020
    Prev
    Next
    INDEX
    Explanations

    fer

    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
     actions
    -0.32
    ench
    -0.30
    ote
    -0.29
    иÑĤел
    -0.28
    otes
    -0.28
    IN
    -0.27
    iveness
    -0.27
     trùng
    -0.27
    iler
    -0.27
    v
    -0.27
    POSITIVE LOGITS
    amat
    0.29
    ccount
    0.28
    æľīéĹ®é¢ĺ
    0.27
    è¯Ħ论
    0.26
    _HIT
    0.23
    廣åijĬ
    0.23
    æĺĨä»ij
    0.23
    çĨĬçĮ«
    0.23
    éĢĢå½¹
    0.23
    astery
    0.23
    Activations Density 0.012%

    No Known Activations