© 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. 53203
    Prev
    Next
    INDEX
    Explanations

    code

    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
    åĮĸ
    -0.29
     Entre
    -0.26
    zier
    -0.26
    家åħ¬åı¸
    -0.25
     bins
    -0.25
     Employees
    -0.25
    åĩ»
    -0.25
    Bins
    -0.25
     Exec
    -0.25
    agen
    -0.24
    POSITIVE LOGITS
    ãģĬãģĦ
    0.26
    orch
    0.26
    NIL
    0.26
    è¢ĸ
    0.25
    nil
    0.25
    æĭ±
    0.25
    *))
    0.24
    undy
    0.24
    illos
    0.23
    á»įng
    0.23
    Activations Density 0.010%

    No Known Activations