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. 23-RESID-POST-AA
    6. 354
    Prev
    Next
    INDEX
    Explanations

    printf

    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
     feeder
    -0.07
    ae
    -0.07
    际
    -0.07
    onder
    -0.07
    	as
    -0.07
     Belgi
    -0.07
    far
    -0.07
    _beh
    -0.06
    Tot
    -0.06
     lokal
    -0.06
    POSITIVE LOGITS
    机构
    0.07
     евр
    0.07
     sofas
    0.07
     fuels
    0.07
    콜
    0.07
    ﺈ
    0.07
     והמ
    0.07
    -Cola
    0.07
     phẩm
    0.07
     perks
    0.07
    Activations Density 0.003%

    No Known Activations