INDEX

Explanations

unstructured text

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

è¾Ľ

-0.29

åı±

-0.26

å¥ı

-0.25

éĢĿ

-0.25

 indifference

-0.25

Fine

-0.24

åħ¥çĿ¡

-0.24

âĶ¤

-0.24

ç³»

-0.24

 Fine

-0.24

POSITIVE LOGITS

ibase

0.26

ç«¯

0.25

.reflect

0.25

éľ²

0.25

çĻ½çĻ½

0.24

å¤©ä½¿

0.24

\Module

0.24

ittest

0.23

eil

0.23

enny

0.23

Activations Density 0.487%

unstructured text

No Comments

No Known Activations