Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 36508
    Prev
    Next
    INDEX
    Explanations

    animals and foreign languages

    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
    확
    -0.08
    拥挤
    -0.07
     faucet
    -0.07
    	Check
    -0.07
    罴
    -0.07
    �
    -0.07
     bereits
    -0.07
    ()._
    -0.07
    .parts
    -0.07
    äch
    -0.06
    POSITIVE LOGITS
    同事们
    0.07
     attacker
    0.06
     imm
    0.06
    UILTIN
    0.06
     applauded
    0.06
    が始ま
    0.06
     Jesus
    0.06
    心意
    0.06
    ไทย
    0.06
    Better
    0.06
    Activations Density 0.004%

    No Known Activations