Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 48452
    Prev
    Next
    INDEX
    Explanations

    less than sign

    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
     structure
    -0.07
     DU
    -0.06
     carc
    -0.06
    .pageSize
    -0.06
    𝘤
    -0.06
     visceral
    -0.06
     Pe
    -0.06
    có
    -0.06
    Um
    -0.06
    舌尖
    -0.06
    POSITIVE LOGITS
     �
    0.08
    共和
    0.07
     enemy
    0.07
    error
    0.06
    年产
    0.06
    awai
    0.06
    帝王
    0.06
    淫
    0.06
    PWM
    0.06
    產
    0.06
    Activations Density 0.017%

    No Known Activations