INDEX

Explanations

om

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

arn

-0.30

 affidavit

-0.28

uster

-0.28

_headers

-0.26

æĦıå¤§

-0.25

 assess

-0.25

amic

-0.25

ounsel

-0.24

ails

-0.23

antas

-0.23

POSITIVE LOGITS

isms

0.27

itches

0.27

æ´ŀ

0.26

çİ°è±¡

0.25

 conf

0.25

èĬĤ

0.25

åĴĮå¹³

0.24

 flat

0.24

ä¼ı

0.24

smarty

0.23

Activations Density 0.001%

om

No Comments

No Known Activations