INDEX

Explanations

delimiters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shepherd

-0.28

 outreach

-0.26

VER

-0.26

 Outreach

-0.25

rust

-0.25

-reply

-0.25

åĳ¨åĪĬ

-0.24

æıĲè®®

-0.24

edith

-0.24

 StringBuffer

-0.24

POSITIVE LOGITS

éħĴ

0.27

do

0.27

éħĴä¸ļ

0.25

bor

0.24

ope

0.24

éĨĩ

0.24

 MyApp

0.24

 config

0.24

é«ĺèĢĥ

0.24

essor

0.24

Activations Density 0.794%

delimiters

No Comments

No Known Activations