© 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. 53347
    Prev
    Next
    INDEX
    Explanations

    grow

    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
    isl
    -0.30
     sl
    -0.29
    ci
    -0.28
    -ag
    -0.28
    ÅĽÄĩ
    -0.28
     ag
    -0.28
    -l
    -0.27
    xAF
    -0.27
     pl
    -0.27
    zz
    -0.26
    POSITIVE LOGITS
    ehr
    0.33
    INO
    0.28
    å¢ŀéķ¿
    0.28
     onBind
    0.27
    eo
    0.26
    efd
    0.26
    tracts
    0.25
    dds
    0.25
    ocs
    0.25
    opsis
    0.25
    Activations Density 0.002%

    No Known Activations