INDEX

Explanations

a/an

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eres

-0.27

 only

-0.27

Only

-0.27

 tráºŃn

-0.26

[float

-0.25

 Only

-0.25

 ONLY

-0.25

only

-0.25

ares

-0.24

ONLY

-0.24

POSITIVE LOGITS

å¤§åŃ¦æ¯ķä¸ļ

0.28

éķ¿å¤§äºĨ

0.26

 Sark

0.26

occup

0.25

 belie

0.25

 broadcasters

0.25

addListener

0.25

æĸ°éĹ»åıĳå¸ĥ

0.24

orthand

0.23

æĽ¿

0.23

Activations Density 0.933%

a/an

No Comments

No Known Activations