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. 24398
    Prev
    Next
    INDEX
    Explanations

    Information technology

    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
    杀人
    -0.06
     стра
    -0.06
    ﮫ
    -0.06
    ㉰
    -0.06
    обра
    -0.06
    .compiler
    -0.06
    pras
    -0.06
    酎
    -0.06
    (center
    -0.06
     explaining
    -0.06
    POSITIVE LOGITS
     INFORMATION
    0.07
    VERT
    0.07
     irregular
    0.07
    微生物
    0.07
     Mathematical
    0.07
    _MIN
    0.07
    满了
    0.07
    اريخ
    0.07
    			 
    0.07
    TREE
    0.07
    Activations Density 0.043%

    No Known Activations