INDEX

Explanations

prepositions

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

 Budget

-0.29

é£¨

-0.26

atoire

-0.25

Budget

-0.24

 basket

-0.24

ä¹ĭæĺŁ

-0.24

 Starr

-0.24

rese

-0.24

_budget

-0.23

LERÄ°

-0.23

POSITIVE LOGITS

orphic

0.28

umba

0.27

©

0.27

éľ²

0.25

emb

0.25

istence

0.25

åľ¨è¿ĩæ¸¡

0.25

AdminController

0.25

Ã¢m

0.24

ä¿ĿèŃ·

0.24

Activations Density 0.004%

prepositions

No Comments

No Known Activations