© 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. 24-TRANSCODER-HP
    7. 150009
    Prev
    Next
    INDEX
    Explanations

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĤĭ
    -0.27
     Denied
    -0.26
    &C
    -0.26
    /tutorial
    -0.26
    olk
    -0.26
    -negative
    -0.25
    negative
    -0.25
    -Nov
    -0.25
    åĿĬ
    -0.25
    SEG
    -0.24
    POSITIVE LOGITS
    æ²»çIJĨä½ĵç³»
    0.26
     Pars
    0.25
     magnitude
    0.24
    mut
    0.24
     existential
    0.23
     exempt
    0.23
    çĤ¹å¤ļ
    0.23
    身为
    0.23
    º«
    0.23
    æ¡¡
    0.23
    Activations Density 1.036%

    No Known Activations