© 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. 53646
    Prev
    Next
    INDEX
    Explanations

    research

    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
     Teams
    -0.43
    Team
    -0.43
     Team
    -0.43
    Teams
    -0.42
    teams
    -0.38
     teams
    -0.35
    TEAM
    -0.35
    _teams
    -0.35
    _team
    -0.35
    åĽ¢éĺŁ
    -0.33
    POSITIVE LOGITS
    bih
    0.32
     t
    0.29
     gr
    0.28
    -separated
    0.27
    tha
    0.26
    ÑĤ
    0.25
     ge
    0.25
    gr
    0.25
     headquartered
    0.25
    b
    0.24
    Activations Density 0.012%

    No Known Activations