© 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. 53807
    Prev
    Next
    INDEX
    Explanations

    period

    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
    å·³
    -0.27
    boats
    -0.27
     boats
    -0.26
     relic
    -0.26
     ships
    -0.26
     Riv
    -0.26
    æ¸ħé¦Ļ
    -0.26
    eti
    -0.26
    uur
    -0.25
     crunch
    -0.25
    POSITIVE LOGITS
     Aren
    0.29
    I
    0.28
     change
    0.27
     Perception
    0.27
     Cinema
    0.26
    (Is
    0.26
    Identity
    0.26
     tag
    0.25
    /change
    0.25
    Is
    0.25
    Activations Density 0.043%

    No Known Activations