© 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. 23-RESID-POST-AA
    11. 724
    Prev
    Next
    INDEX
    Explanations

    any

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ald
    -0.07
     guid
    -0.07
     padded
    -0.06
    告诉他
    -0.06
    дж
    -0.06
    參
    -0.06
    否則
    -0.06
    baseline
    -0.06
    getting
    -0.06
    ******
↵
    -0.06
    POSITIVE LOGITS
    .opensource
    0.07
     Arn
    0.07
     Rochester
    0.07
    /access
    0.07
     Justiça
    0.07
     Estate
    0.07
     PHONE
    0.07
     Hort
    0.07
    	K
    0.07
     Roulette
    0.07
    Activations Density 0.000%

    No Known Activations