INDEX

Explanations

starting sentences/clauses

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

arro

-0.29

 analyse

-0.28

 deriv

-0.28

-analysis

-0.28

ç¿»

-0.26

apot

-0.26

anal

-0.26

al

-0.25

 revers

-0.25

 analys

-0.25

POSITIVE LOGITS

åĸĩåıŃ

0.26

baum

0.26

xbc

0.25

 Ð¾Ð±ÑıÐ·Ð°Ð½

0.24

.cls

0.24

tÄ±r

0.24

_EXEC

0.24

ä¹ł

0.23

 peeled

0.23

EMBER

0.23

Activations Density 0.027%

starting sentences/clauses

No Comments

No Known Activations