INDEX

Explanations

accounts, programming, medicine

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

compress

-0.27

pressor

-0.25

hazi

-0.25

 Slug

-0.25

 ['',

-0.25

 massages

-0.24

 prix

-0.24

buster

-0.24

 Yourself

-0.24

atron

-0.23

POSITIVE LOGITS

 coincidence

0.29

 empirical

0.27

.TextAlignment

0.26

ç»ıéªĮ

0.26

 call

0.26

templ

0.26

0.25

å¸Ĥæ°ĳ

0.25

dot

0.25

enn

0.25

Activations Density 0.009%

accounts, programming, medicine

No Comments

No Known Activations