INDEX

Explanations

flow

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĩıåħį

-0.26

awns

-0.25

åĬ³åĬ¨

-0.24

 hazard

-0.24

eca

-0.23

Ð²Ð°ÑĤ

-0.23

æĴ¸

-0.23

 survives

-0.23

Tro

-0.23

_lab

-0.23

POSITIVE LOGITS

DL

0.28

 Loop

0.27

ÑģÐ¾Ð²

0.25

æ¶Į

0.25

æ¿ł

0.24

LastError

0.23

.kotlin

0.23

axy

0.23

Ð½Ð¾ÑģÑĤÑĮÑİ

0.23

æ®µ

0.23

Activations Density 0.031%

flow

No Comments

No Known Activations