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. 89054
    Prev
    Next
    INDEX
    Explanations

    Formal/Technical writing

    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
     meaningful
    -0.07
    դ
    -0.07
    ures
    -0.06
    .total
    -0.06
    장님
    -0.06
    产业结构
    -0.06
    焘
    -0.06
    Martin
    -0.06
     achieving
    -0.06
     ullam
    -0.06
    POSITIVE LOGITS
     freq
    0.09
    (%
    0.07
    sembling
    0.07
    programs
    0.07
     DAYS
    0.07
     FIXED
    0.07
    .manual
    0.07
     �
    0.07
    sequence
    0.07
    versions
    0.07
    Activations Density 0.051%

    No Known Activations