INDEX

Explanations

Analysis

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĶ¾åģĩ

-0.31

çĿĢæĢ¥

-0.30

åħĪæĬĬ

-0.29

è¦ļãģĪ

-0.27

èººçĿĢ

-0.27

<$

-0.26

æı¡

-0.26

acter

-0.25

å¼ĺ

-0.24

áºŃu

-0.24

POSITIVE LOGITS

loff

0.30

æ®Ĩ

0.26

wal

0.25

Amb

0.25

>>)

0.25

 contributions

0.25

cano

0.24

 eing

0.24

Amb

0.24

 bent

0.24

Activations Density 0.214%

Analysis

No Comments

No Known Activations