© 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. 53639
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    aga
    -0.29
    slt
    -0.28
    åģ¥
    -0.27
    åĬ©
    -0.27
    statt
    -0.27
    夷
    -0.26
    prep
    -0.25
     masturbation
    -0.25
    shr
    -0.25
    ä¿ĥ
    -0.25
    POSITIVE LOGITS
    ele
    0.27
    éªĵ
    0.26
    師
    0.26
    å¥ijæľº
    0.26
    dae
    0.26
    dbe
    0.25
    dcc
    0.25
    河边
    0.24
    -Jun
    0.24
    éģ¿
    0.24
    Activations Density 0.010%

    No Known Activations