INDEX

Explanations

Rap

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

å¸ĥå±Ģ

-0.35

 architectural

-0.34

å»ºçŃĳå¸Ī

-0.29

Construction

-0.29

 architect

-0.28

å»ºçŃĳè®¾è®¡

-0.28

thouse

-0.27

 coastline

-0.27

ayout

-0.26

 architecture

-0.26

POSITIVE LOGITS

icer

0.32

è¯¬

0.28

 +=↵

0.27

erton

0.25

port

0.25

_TYP

0.25

äººæ¬¡

0.25

uzz

0.24

éĦľ

0.24

uchos

0.23

Activations Density 0.022%

Rap

No Comments

No Known Activations