INDEX

Explanations

out

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¡£

-0.29

facet

-0.28

 facet

-0.27

æŀ¨

-0.27

èµ·äºĨ

-0.26

rat

-0.26

 favor

-0.25

np

-0.24

functional

-0.24

 ratified

-0.24

POSITIVE LOGITS

ottle

0.26

NECT

0.26

à¹ģà¸¡

0.25

acle

0.25

illing

0.25

etwork

0.25

çĽĳ

0.24

emics

0.24

_look

0.23

 cams

0.23

Activations Density 0.001%

out

No Comments

No Known Activations