© 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. 53031
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    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
    æ¤İ
    -0.25
    åĨµ
    -0.25
    å±
    -0.25
    @gmail
    -0.24
    ustralian
    -0.24
    ews
    -0.24
    aurant
    -0.23
    lect
    -0.23
    (Local
    -0.23
    -scenes
    -0.23
    POSITIVE LOGITS
    éĽĨåĽ¢èĤ¡ä»½
    0.28
    ajo
    0.27
     legitimately
    0.26
     appearance
    0.25
     Grimm
    0.24
    matcher
    0.24
     appearances
    0.24
    tré
    0.23
    itra
    0.23
    itat
    0.23
    Activations Density 0.647%

    No Known Activations