© 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. 39728
    Prev
    Next
    INDEX
    Explanations

    small units of measurement

    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
     def
    -0.63
     met
    -0.47
    	def
    -0.47
    Met
    -0.45
    def
    -0.43
     Met
    -0.42
    met
    -0.42
    _met
    -0.36
     metall
    -0.35
    omet
    -0.33
    POSITIVE LOGITS
    IVES
    0.31
    ives
    0.28
    ipeg
    0.28
    wit
    0.27
    ival
    0.26
    ISTRIBUT
    0.26
    rades
    0.25
    ORB
    0.25
    rones
    0.25
    ä¸ĢæīĢ
    0.25
    Activations Density 0.005%

    No Known Activations