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. 15-RESID-POST-AA
    6. 45854
    Prev
    Next
    INDEX
    Explanations

    fantasy

    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
     Vaccine
    -0.09
    漕
    -0.08
     características
    -0.08
    缪
    -0.08
     Cic
    -0.07
    تفسير
    -0.07
    ẍ
    -0.07
    ewe
    -0.07
    ahun
    -0.07
     Arabian
    -0.06
    POSITIVE LOGITS
    nullable
    0.08
    人气
    0.08
    Remaining
    0.07
    那时
    0.07
    lator
    0.07
    -manager
    0.07
     concat
    0.07
    立
    0.07
    .btnAdd
    0.07
    	config
    0.06
    Activations Density 0.003%

    No Known Activations