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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22762
    Prev
    Next
    INDEX
    Explanations

    let

    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
    栒
    -0.07
    缁
    -0.07
     تش
    -0.07
     Dry
    -0.07
    ⇋
    -0.07
    rem
    -0.07
    汋
    -0.07
     Sponge
    -0.07
     soph
    -0.07
     spar
    -0.06
    POSITIVE LOGITS
     bahwa
    0.07
    Control
    0.07
    ANEL
    0.07
     moderated
    0.07
     peculiar
    0.07
    clientes
    0.06
    control
    0.06
    ',
↵
    0.06
     ***↵
    0.06
    Gateway
    0.06
    Activations Density 0.017%

    No Known Activations