© 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. 32-TRANSCODER-HP
    7. 41575
    Prev
    Next
    INDEX
    Explanations

    venting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     self
    -0.53
    self
    -0.51
     Self
    -0.45
    	self
    -0.45
    (self
    -0.44
    -self
    -0.44
    Self
    -0.42
    :self
    -0.41
    <Self
    -0.40
     SELF
    -0.40
    POSITIVE LOGITS
    åĪ°ä½į
    0.30
    ä¸ĬéŨ
    0.28
    .hasMore
    0.28
    ducted
    0.26
    çļĦåĪ°æĿ¥
    0.25
    .IP
    0.25
    éĺĶ
    0.25
    ynchron
    0.24
    è¸ıå®ŀ
    0.24
    esterday
    0.24
    Activations Density 0.008%

    No Known Activations