INDEX

Explanations

cerv

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

Not in Any Lists

No Comments

Negative Logits

ä»ĸä»¬çļĦ

-0.29

 their

-0.28

acos

-0.27

æīŃ

-0.26

Their

-0.26

ks

-0.26

æ¦ķ

-0.26

jas

-0.26

 THEIR

-0.26

ODB

-0.25

POSITIVE LOGITS

eer

0.30

éĿ¢

0.25

 defer

0.25

å¹´æĿ¥

0.25

een

0.25

imers

0.24

 Bond

0.24

unter

0.23

[h

0.23

ertext

0.23

Activations Density 0.005%

cerv

No Comments

No Known Activations