© 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. 22753
    Prev
    Next
    INDEX
    Explanations

    Julian or Ian

    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
    民用
    -0.07
    햠
    -0.07
     smell
    -0.07
     regret
    -0.07
     admit
    -0.07
    igner
    -0.07
    .Cl
    -0.06
    _kill
    -0.06
    _crit
    -0.06
    resenter
    -0.06
    POSITIVE LOGITS
    叫做
    0.07
    との
    0.07
    经费
    0.07
    進行
    0.07
     PERFORMANCE
    0.07
    很快
    0.07
    	address
    0.07
     processing
    0.07
    长期以来
    0.07
    作坊
    0.07
    Activations Density 0.034%

    No Known Activations