INDEX

Explanations

work

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

iger

-0.30

iphy

-0.27

PTION

-0.25

inton

-0.25

dependencies

-0.25

ä½¿äºº

-0.24

åħ¬åĽŃ

-0.24

çī¹åĪ«å£°æĺİ

-0.24

çº¯çĶµåĬ¨

-0.24

UnitTest

-0.23

POSITIVE LOGITS

æĬĸ

0.32

tup

0.27

Ci

0.26

 Exist

0.25

 existence

0.24

æĶ¥

0.24

Ci

0.24

ħ§

0.24

éĶľ

0.24

 part

0.24

Activations Density 0.007%

work

No Comments

No Known Activations