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. 19-RESID-POST-AA
    6. 24346
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ricing
    -0.07
    _TO
    -0.07
     terribly
    -0.07
    _REFERENCE
    -0.07
     CCD
    -0.07
    ﻨ
    -0.07
    .cell
    -0.07
    .encoder
    -0.07
    .SetText
    -0.07
    .Mockito
    -0.07
    POSITIVE LOGITS
     show
    0.08
     item
    0.07
     certain
    0.07
    htm
    0.07
    看了一
    0.07
    ях
    0.07
    說明
    0.07
    скую
    0.07
    "]==
    0.06
     organization
    0.06
    Activations Density 0.085%

    No Known Activations