INDEX

Explanations

VR

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Connection

-0.29

Connection

-0.28

gel

-0.27

 connection

-0.27

 spec

-0.26

åĪ°æĿ¥

-0.26

ËĲ

-0.26

é©³

-0.26

 connections

-0.25

appl

-0.25

POSITIVE LOGITS

aign

0.26

åħ¨å¥Ĺ

0.26

aits

0.26

èĬ®

0.24

gis

0.24

itters

0.24

semblies

0.24

åħ¨æĻ¯

0.23

 expectation

0.23

 destruct

0.23

Activations Density 0.065%

VR

No Comments

No Known Activations