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. 48817
    Prev
    Next
    INDEX
    Explanations

    Beginning of sentences

    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
    Voice
    -0.07
     اختيار
    -0.07
     cousins
    -0.07
     vient
    -0.07
    ppe
    -0.07
     recommended
    -0.07
    home
    -0.07
     chose
    -0.07
     ולכן
    -0.06
    ItemImage
    -0.06
    POSITIVE LOGITS
    拘
    0.07
    𪩘
    0.06
    itored
    0.06
     Higher
    0.06
    钻研
    0.06
    䗪
    0.06
     Hyper
    0.06
    -exp
    0.06
    �
    0.06
     HOWEVER
    0.06
    Activations Density 0.150%

    No Known Activations