© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41106
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Bennett
    -0.08
    	Double
    -0.07
    年来
    -0.07
    YYY
    -0.06
     "-",
    -0.06
    "،
    -0.06
    集团
    -0.06
     Encounter
    -0.06
    /org
    -0.06
    IT
    -0.06
    POSITIVE LOGITS
    自家
    0.07
     rsp
    0.07
     função
    0.07
    tein
    0.07
    梌
    0.07
     top
    0.06
    彤
    0.06
    ましたが
    0.06
    天下
    0.06
    Granted
    0.06
    Activations Density 0.236%

    No Known Activations