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. 70759
    Prev
    Next
    INDEX
    Explanations

    Job postings and software listings

    np_max-act-logits · gemini-2.0-flash
    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
    اريخ
    -0.07
    akit
    -0.07
     divid
    -0.07
    𝙀
    -0.06
    仲裁
    -0.06
    dispatch
    -0.06
     speaks
    -0.06
    僻
    -0.06
    issued
    -0.06
    疽
    -0.06
    POSITIVE LOGITS
     billboard
    0.07
    过错
    0.07
     Average
    0.07
    홀
    0.06
     Rover
    0.06
     fallback
    0.06
    浴室
    0.06
     TO
    0.06
    правля
    0.06
     Transitional
    0.06
    Activations Density 0.002%

    No Known Activations