INDEX

Explanations

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

!_

-0.29

ä¸ªæľĪåĨħ

-0.25

_br

-0.25

]][

-0.24

(tk

-0.24

oucher

-0.23

 infix

-0.23

åħ¼é¡¾

-0.23

ä¿¸

-0.23

PTS

-0.23

POSITIVE LOGITS

 military

0.28

æĽ²æĬĺ

0.28

uish

0.28

åĨĽ

0.27

ettle

0.25

ilitation

0.25

ÑĨÐ¸Ð¿

0.25

 Ð²Ð¾

0.24

sink

0.24

 sinking

0.24

Activations Density 0.031%

the

No Known Activations