Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 27316
    Prev
    Next
    INDEX
    Explanations

    varied text snippets

    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
     borderline
    -0.07
    曾经
    -0.06
     Tub
    -0.06
    ("");↵
    -0.06
    .cz
    -0.06
    有着
    -0.06
     pieces
    -0.06
     deductible
    -0.06
    ๆ
    -0.06
    uchi
    -0.06
    POSITIVE LOGITS
    鬷
    0.09
    莅
    0.08
     comport
    0.07
    تمويل
    0.07
    สำค
    0.07
    AuthProvider
    0.07
    ╖
    0.07
     оригинал
    0.07
    DidAppear
    0.07
    zzle
    0.07
    Activations Density 0.074%

    No Known Activations