© 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. 54166
    Prev
    Next
    INDEX
    Explanations

    trans

    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
    eko
    -0.30
    ayload
    -0.29
    eyed
    -0.29
    estar
    -0.28
    ele
    -0.28
    ee
    -0.28
    efa
    -0.28
    å¾·å°Ķ
    -0.27
    eling
    -0.27
    tics
    -0.27
    POSITIVE LOGITS
    mit
    0.30
    gres
    0.29
    .onCreate
    0.27
    mite
    0.26
    loc
    0.26
    cri
    0.26
    duce
    0.26
    mites
    0.25
    criptions
    0.25
    mute
    0.25
    Activations Density 0.036%

    No Known Activations