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. 170
    Prev
    Next
    INDEX
    Explanations

    assassinations

    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
     tow
    -0.07
    歧视
    -0.07
     arguing
    -0.06
    lene
    -0.06
    rieg
    -0.06
     sightings
    -0.06
    שהו
    -0.06
     prohibiting
    -0.06
     Roosevelt
    -0.06
    licted
    -0.06
    POSITIVE LOGITS
     UserDefaults
    0.08
    ereço
    0.07
     Jeb
    0.07
     Cald
    0.07
     Elementary
    0.07
     wnętrz
    0.07
    =text
    0.07
     membranes
    0.07
     предмет
    0.07
    爸妈
    0.07
    Activations Density 0.012%

    No Known Activations