INDEX

Explanations

time-related texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿ħéĢŁ

-0.29

å¿«éĢŁ

-0.28

Rev

-0.28

 quickly

-0.27

 rapid

-0.26

 rapidly

-0.26

 Quickly

-0.26

Rev

-0.26

æľīä¸Ģæ¬¡

-0.25

ventions

-0.25

POSITIVE LOGITS

âĢ¦”↵↵

0.28

Ð¾Ð²Ð°Ð½Ð¸Ðµ

0.27

ãģ¾ãģĦ

0.26

_IA

0.26

å¹³åĿ¦

0.25

ofilm

0.25

vig

0.25

vag

0.25

isel

0.24

OLF

0.24

Activations Density 0.002%

time-related texts

No Comments

No Known Activations