© 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 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. 74842
    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
    /ros
    -0.07
     seks
    -0.07
     insulation
    -0.07
    习近
    -0.07
     Folk
    -0.07
    简约
    -0.07
    -score
    -0.07
    (Graph
    -0.07
     Por
    -0.06
    (relative
    -0.06
    POSITIVE LOGITS
    说自己
    0.07
     santa
    0.06
    """.
    0.06
    fre
    0.06
     Mission
    0.06
     aa
    0.06
    ISTORY
    0.06
    行动
    0.06
    /moment
    0.06
    无人
    0.06
    Activations Density 0.169%

    No Known Activations