© 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. 53206
    Prev
    Next
    INDEX
    Explanations

    Activities and organizations

    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
    è®°
    -0.30
     gen
    -0.30
     SPDX
    -0.26
    ials
    -0.26
    éĽĨ
    -0.26
     proper
    -0.25
     strong
    -0.25
    ress
    -0.25
    _mem
    -0.24
    sys
    -0.24
    POSITIVE LOGITS
     Clinic
    0.28
    fé
    0.26
    ä½łè§īå¾Ĺ
    0.25
    abh
    0.25
    /Library
    0.25
    ‘s
    0.25
     Certification
    0.24
    è¯ĬæīĢ
    0.24
    fad
    0.24
    мÑĭ
    0.24
    Activations Density 0.010%

    No Known Activations