INDEX

Explanations

za

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uyáº¿n

-0.28

ECH

-0.28

iator

-0.27

å¯¹èĩªå·±

-0.27

ä»ĸåıĪ

-0.27

æª«

-0.26

 paralle

-0.25

MES

-0.24

SingleNode

-0.24

uating

-0.24

POSITIVE LOGITS

çļĦè¿ĽæŃ¥

0.27

å¹´æĿ¥

0.26

mallow

0.25

æĸ°æīĭ

0.25

æľ¬æĬ¥

0.24

 surve

0.24

æ¨¡èĮĥ

0.23

å°ıæĹ¶åīį

0.23

 VIII

0.23

-append

0.23

Activations Density 24.704%

za

No Comments

No Known Activations