© 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. 11-RESID-POST-AA
    11. 29401
    Prev
    Next
    INDEX
    Explanations

    standards and safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     homeowners
    -0.08
    mpi
    -0.07
    ()=="
    -0.07
    间接
    -0.07
     inst
    -0.07
     Miller
    -0.07
     Holding
    -0.07
    ]()↵
    -0.06
     Each
    -0.06
     peer
    -0.06
    POSITIVE LOGITS
    觫
    0.08
    �
    0.07
    ricia
    0.07
    ANNOT
    0.07
    ได
    0.07
    Measured
    0.06
    )return
    0.06
    \Web
    0.06
    💒
    0.06
    绝大多数
    0.06
    Activations Density 0.219%

    No Known Activations