© 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. 54239
    Prev
    Next
    INDEX
    Explanations

    music and coding

    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
     discrim
    -0.27
    å¼ĢéŨ
    -0.27
    ä¸ĭåİ»
    -0.27
    ometrics
    -0.26
     przec
    -0.24
    RE
    -0.24
    itel
    -0.24
    rops
    -0.24
     pret
    -0.24
    ä¸ģ
    -0.24
    POSITIVE LOGITS
    éĴĪ
    0.32
    æľ½
    0.26
    olon
    0.25
     Edmonton
    0.24
    leo
    0.23
     Halifax
    0.23
     IPV
    0.23
    è·Įå¹ħ
    0.23
    åĩºåľº
    0.23
    ocol
    0.23
    Activations Density 0.011%

    No Known Activations