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. 23-RESID-POST-AA
    6. 231
    Prev
    Next
    INDEX
    Explanations

    Plus or minus

    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
     Helpful
    -0.07
    桕
    -0.07
     Tampa
    -0.07
    	cp
    -0.07
     commonly
    -0.07
    Spring
    -0.07
    豕
    -0.07
     charset
    -0.07
    夏
    -0.07
    LOOK
    -0.06
    POSITIVE LOGITS
    =forms
    0.07
    💣
    0.07
    intégr
    0.06
     timeouts
    0.06
    古典
    0.06
     continuity
    0.06
    崌
    0.06
    ników
    0.06
     أكد
    0.06
     nhân
    0.06
    Activations Density 0.008%

    No Known Activations