© 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. 15-RESID-POST-AA
    6. 123662
    Prev
    Next
    INDEX
    Explanations

    mollusks

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חודשים
    -0.08
     residency
    -0.07
    [temp
    -0.07
     puberty
    -0.07
    setId
    -0.07
     legally
    -0.07
    tığı
    -0.07
    딲
    -0.07
    ennen
    -0.07
     кто
    -0.07
    POSITIVE LOGITS
     Vuex
    0.07
    \">↵
    0.07
    四是
    0.07
    ("/",
    0.07
    systems
    0.07
    ={`${
    0.07
    	has
    0.06
    parms
    0.06
     abolish
    0.06
    さえ
    0.06
    Activations Density 0.000%

    No Known Activations