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. 15-RESID-POST-AA
    6. 110296
    Prev
    Next
    INDEX
    Explanations

    Eighth Circuit court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scopes
    -0.07
    Doctors
    -0.07
    出来的
    -0.07
     Governors
    -0.07
     Tactics
    -0.07
    見積もり
    -0.07
    踏实
    -0.07
    ------------
    -0.07
     memorable
    -0.07
    /ui
    -0.07
    POSITIVE LOGITS
     sobre
    0.07
    ṇ
    0.07
     Ag
    0.07
    즌
    0.07
     synerg
    0.06
    �
    0.06
     bin
    0.06
     alg
    0.06
     фин
    0.06
    增资
    0.06
    Activations Density 0.013%

    No Known Activations