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

    Neuronpedia

    APICircuit 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. 31221
    Prev
    Next
    INDEX
    Explanations

    forum

    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
     chains
    -0.08
     XI
    -0.08
     beauty
    -0.07
    Pl
    -0.07
    Death
    -0.07
     resemble
    -0.07
     toss
    -0.07
    ropy
    -0.07
    'Brien
    -0.06
     uniquely
    -0.06
    POSITIVE LOGITS
    坊
    0.08
     forums
    0.08
    _pcm
    0.08
    热闹
    0.07
    \param
    0.07
     forum
    0.07
    议事
    0.07
    .setVisible
    0.07
    샏
    0.06
    cad
    0.06
    Activations Density 0.006%

    No Known Activations