© 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. 40024
    Prev
    Next
    INDEX
    Explanations

    objective C code

    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
    MM
    -0.34
    MB
    -0.32
    PD
    -0.30
    PN
    -0.29
    MP
    -0.29
    RM
    -0.29
    PM
    -0.29
    PB
    -0.28
    MR
    -0.28
    BM
    -0.27
    POSITIVE LOGITS
     Ц
    0.70
     setC
    0.69
    getC
    0.69
     CX
    0.68
     Cv
    0.66
    Cx
    0.66
     CSC
    0.65
     getC
    0.65
    å®ĭ
    0.65
     Ci
    0.63
    Activations Density 11.913%

    No Known Activations