© 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. 27-TRANSCODER-HP
    7. 57172
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    代çIJĨ
    -0.27
     LOSS
    -0.27
    -gradient
    -0.26
    åĿıäºĭ
    -0.25
     synthetic
    -0.25
    å©·
    -0.25
    :ss
    -0.25
    umatic
    -0.25
     worse
    -0.25
    ume
    -0.25
    POSITIVE LOGITS
     able
    0.34
    èĥ½å¾ĹåĪ°
    0.33
    تÙħÙĥÙĨ
    0.30
    èĥ½æī¾åĪ°
    0.30
    èĥ½æĬĬ
    0.27
    å°±èĥ½
    0.27
    èĥ½å¤Łåľ¨
    0.26
    ifr
    0.26
     poder
    0.26
     receiving
    0.26
    Activations Density 0.004%

    No Known Activations