© 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. 35-TRANSCODER-HP
    7. 39023
    Prev
    Next
    INDEX
    Explanations

    Code and inventions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otas
    -0.27
    otos
    -0.26
    creenshot
    -0.25
    intage
    -0.24
     followed
    -0.24
    .solution
    -0.24
    ãĥĽãĥ¼ãĥ«
    -0.24
     retract
    -0.23
     fils
    -0.23
    heels
    -0.23
    POSITIVE LOGITS
    åĥı
    0.58
    象
    0.54
     like
    0.46
    like
    0.45
    Like
    0.43
    åĥıæĺ¯
    0.41
    åı¯èĥ½
    0.40
     Like
    0.40
     possible
    0.36
    -like
    0.34
    Activations Density 17.028%

    No Known Activations