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. 27881
    Prev
    Next
    INDEX
    Explanations

    compile/assemble

    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
    Well
    -0.07
     cours
    -0.07
    .setModel
    -0.07
    Ƭ
    -0.06
    ################
    -0.06
    为之
    -0.06
    Ϊ
    -0.06
    .asInstanceOf
    -0.06
    Months
    -0.06
    ⌡
    -0.06
    POSITIVE LOGITS
     alcuni
    0.07
    ernet
    0.07
    -packed
    0.07
     assembling
    0.07
     transplant
    0.07
    洁
    0.06
    水稻
    0.06
    /sl
    0.06
    ernational
    0.06
     SMB
    0.06
    Activations Density 0.064%

    No Known Activations