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. 19-RESID-POST-AA
    6. 131057
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    加快发展
    -0.07
    =fopen
    -0.07
     consisted
    -0.07
    bben
    -0.07
    |.
    -0.07
    	REQUIRE
    -0.07
    ContentPane
    -0.07
    쑨
    -0.07
    พวก
    -0.07
    柈
    -0.06
    POSITIVE LOGITS
     раз
    0.08
    _AD
    0.07
     lup
    0.07
    แล
    0.07
     metabol
    0.07
    嫉妒
    0.07
    ἦ
    0.07
     dazzling
    0.06
    Got
    0.06
    .jpa
    0.06
    Activations Density 0.013%

    No Known Activations