© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 78003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Javadoc
    -0.07
    #######↵
    -0.07
     hope
    -0.07
    \P
    -0.07
    /testing
    -0.07
     dec
    -0.07
    ’ex
    -0.06
    .save
    -0.06
    section
    -0.06
     testified
    -0.06
    POSITIVE LOGITS
     Zahl
    0.07
     Ceramic
    0.07
     rift
    0.07
    BITS
    0.07
    Ultra
    0.07
    _LIMIT
    0.07
     splendid
    0.06
     LW
    0.06
     astonishing
    0.06
    Bron
    0.06
    Activations Density 0.018%

    No Known Activations