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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 376
    Prev
    Next
    INDEX
    Explanations

    title

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    天下
    -0.09
    (constants
    -0.08
    חד
    -0.07
    \Log
    -0.07
    להלן
    -0.07
     kol
    -0.06
     shrink
    -0.06
     Mẹ
    -0.06
    켜
    -0.06
     leftover
    -0.06
    POSITIVE LOGITS
    >
    ↵
    ↵
    0.07
     Sé
    0.07
    愿望
    0.07
    ۈ
    0.07
    귄
    0.07
     embody
    0.07
    ativity
    0.07
    ү
    0.07
     główne
    0.07
     suede
    0.06
    Activations Density 0.000%

    No Known Activations