INDEX

Explanations

and or

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

çļĦè§Ĵèī²

-0.33

Role

-0.29

(role

-0.28

è§Ĵèī²

-0.27

 role

-0.27

æĪĲé¾Ļ

-0.26

{name

-0.26

 roles

-0.26

çļĦèº«ä»½

-0.26

ERO

-0.25

POSITIVE LOGITS

 vaguely

0.26

prising

0.26

æ¯«

0.25

tery

0.25

å¾®

0.25

 addCriterion

0.24

breaker

0.24

å¾®å¾®

0.24

iling

0.24

aban

0.24

Activations Density 0.027%

and or

No Comments

No Known Activations