© 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
    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. 42230
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    海水
    -0.08
    terminate
    -0.08
     Yorker
    -0.08
     freshmen
    -0.08
     männ
    -0.07
     emacs
    -0.07
    ĸ
    -0.07
    棐
    -0.07
    asurable
    -0.07
     pearls
    -0.07
    POSITIVE LOGITS
    пущен
    0.06
    attice
    0.06
    ]");↵
    0.06
    )));↵
    0.06
     "").
    0.06
     propia
    0.06
    流淌
    0.06
    "];↵
    0.06
     LGBTQ
    0.06
    supply
    0.06
    Activations Density 0.030%

    No Known Activations