INDEX

Explanations

which

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/sbin

-0.26

æĴĤ

-0.25

 Rubin

-0.25

åĭĺæİ¢

-0.24

 Mand

-0.24

issen

-0.24

|/

-0.23

ãĤ·ãĤ§

-0.23

DebugEnabled

-0.23

æģĤ

-0.23

POSITIVE LOGITS

ereg

0.26

lif

0.25

æĸ¹å¼ıè¿Ľè¡Į

0.24

æľĢéķ¿

0.24

opleft

0.24

omat

0.24

 lifetime

0.24

åı¯æĥ³

0.24

ANEL

0.24

unched

0.23

Activations Density 0.001%

which

No Comments

No Known Activations