© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 1322
    Prev
    Next
    INDEX
    Explanations

    Thinking

    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
    ')
↵
↵
    -0.08
    igi
    -0.08
     cv
    -0.08
    oky
    -0.07
    Nor
    -0.07
     francais
    -0.07
    믿
    -0.07
    Connect
    -0.07
    Nb
    -0.07
     include
    -0.07
    POSITIVE LOGITS
    娆
    0.07
    บาย
    0.07
    @RestController
    0.07
     articulated
    0.06
    自动
    0.06
    拂
    0.06
     Containers
    0.06
     Loving
    0.06
     "::
    0.06
    äre
    0.06
    Activations Density 0.055%

    No Known Activations