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. 87805
    Prev
    Next
    INDEX
    Explanations

    Social justice and equity

    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
    おります
    -0.08
    政协委员
    -0.07
    빻
    -0.07
    สนใจ
    -0.07
    갔
    -0.07
    紊
    -0.07
    בל
    -0.07
    OLTIP
    -0.07
    了解一下
    -0.06
     Ocean
    -0.06
    POSITIVE LOGITS
    決
    0.07
     bfd
    0.07
     Doug
    0.07
     ruby
    0.07
     stripping
    0.06
     Mother
    0.06
     Rpc
    0.06
    dance
    0.06
     precip
    0.06
     Tire
    0.06
    Activations Density 0.205%

    No Known Activations