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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 85740
    Prev
    Next
    INDEX
    Explanations

    possibilities

    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
     Söz
    -0.07
    Employee
    -0.07
    ἕ
    -0.07
     yatırım
    -0.07
     }]
    -0.06
    〔
    -0.06
    \Json
    -0.06
    魔法师和
    -0.06
    pyx
    -0.06
     getById
    -0.06
    POSITIVE LOGITS
    algo
    0.07
     Mark
    0.07
    Mark
    0.07
    Downloading
    0.07
    -authored
    0.06
    Mult
    0.06
     jwt
    0.06
     WHETHER
    0.06
    +w
    0.06
     acesso
    0.06
    Activations Density 0.113%

    No Known Activations